Test_transE-2023-11-28.log

Total feature length is: 10, Top 10 namely: ['clusters', 'POI_Type', 'Art&Entertainment', 'Drink', 'Food', 'Nightlife Spot', 'Outdoor', 'School&Office', 'Shop', 'Travel Spot']
clusters max: 10, category max: 260, feature max: 273
Config takes: 18.852882146835327
___Config Done!!___
272
Now Load PN pretrain from ./data-ms/PN-model-ours/PN-model-ours.txt, takes 0.0005483627319335938 seconds.
-----
It has processed 0 episodes
----target item:  5
[2.3468000594751017e-05, 0.9979539486374576, 0.0003020455707131709, 0.00010603887481881478, 0.0003514585691918386, 0.00018137831833410088, 0.00031520297872374245, 0.00022645057596297748, 0.0003711285092636496, 0.0001688799649394527]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2111]
random_location_list [2111]
Random Combined Rec Success! in episode: 0.
Random Combined Rec Success! in episode: 0.
Rec Success! in episode: 0.
total combined:  1
-----
It has processed 1 episodes
----target item:  706
[2.506566508610541e-05, 1.4736520202830847e-05, 0.0002929541278115278, 0.9981033384977164, 0.0003390927084852387, 0.0001749432141663408, 0.0003080465267352915, 0.00021896858539737846, 0.00035859820072071236, 0.00016425595367816368]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995316510212226, 7.375346803576028e-06, 0.00014661794374862676, 0.4995316510212226, 0.00016970942184587934, 8.755573620162928e-05, 0.00015417140105256283, 0.00010958959334808828, 0.00017947154803517077, 8.220696651953569e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33315936634433546, 4.918939295689827e-06, 9.778587830048559e-05, 0.33315936634433546, 0.00011318658853597761, 5.839472540551253e-05, 0.33315936634433546, 7.30900622676086e-05, 0.00011969737472690028, 5.482739846163407e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 1.
Rec Success! in episode: 1.
total combined:  1
-----
It has processed 2 episodes
----target item:  40
[2.719219928922553e-05, 1.657203261211704e-05, 0.9980967585285339, 0.00011398553879835175, 0.0003808386387193815, 0.0001957711615564908, 0.0003408330825375268, 0.000244603077341186, 0.00040075564069444464, 0.0001826900999173444]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49953053454599594, 8.294021835567199e-06, 0.49953053454599594, 5.704783292793973e-05, 0.00019060329286684427, 9.798015287132968e-05, 0.0001705811891042856, 0.00012241970022623325, 0.00020057141525392093, 9.143330292196668e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.33312645924570233, 0.33312645924570233, 0.33312645924570233, 3.804400587483022e-05, 0.00012710934704124067, 6.534091340791356e-05, 0.00011375702506730322, 8.163913606472503e-05, 0.00013375687924695995, 6.097495619005025e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499051760265533, 0.2499051760265533, 0.2499051760265533, 2.8387786615215372e-05, 9.506274505521206e-05, 4.9051793756595894e-05, 0.2499051760265533, 6.111657744778653e-05, 0.00010016626996775361, 4.551072094427267e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2121]
random_location_list [2121]
Random Combined Rec Success! in episode: 2.
Random Combined Rec Success! in episode: 2.
Rec Success! in episode: 2.
total combined:  2
-----
It has processed 3 episodes
----target item:  304
[0.9978900626414264, 1.543574721596373e-05, 0.0003126717447029301, 0.00010986126222582173, 0.00036611170586101733, 0.00018680129595415745, 0.00032581729832571743, 0.00023442257736738413, 0.00038430770318201383, 0.00017450802373868536]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 3.
Rec Success! in episode: 3.
total combined:  2
-----
It has processed 4 episodes
----target item:  1985
[2.641679744873775e-05, 1.544999618565424e-05, 0.00030693320541457436, 0.00010714832170178152, 0.00035932415149206987, 0.0001863794321302088, 0.0003243029118510661, 0.00023063219166934317, 0.9982711590216937, 0.00017225397041287075]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3221857082023088e-05, 7.732869280650937e-06, 0.49964416085270225, 5.362874886211013e-05, 0.00017984513779032557, 9.328466932587968e-05, 0.0001623166759748015, 0.000115433594200175, 0.49964416085270225, 8.62147420795262e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331780825936677, 5.1565148994792254e-06, 0.3331780825936677, 3.5761297975105824e-05, 0.00011992626526549063, 6.22050845312362e-05, 0.00010823774820457711, 7.697466836572923e-05, 0.3331780825936677, 5.749063975518445e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499136279144499, 0.2499136279144499, 0.2499136279144499, 2.682420057860741e-05, 8.995552108774598e-05, 4.6659426781339335e-05, 8.118807852101708e-05, 5.773794746352456e-05, 0.2499136279144499, 4.3123167768100715e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 4.
Rec Success! in episode: 4.
total combined:  2
-----
It has processed 5 episodes
----target item:  541
[0.9978749578454141, 1.5370993553242033e-05, 0.000315414799495803, 0.00010924151768710871, 0.00036513812087669677, 0.00018945171661114994, 0.0003308070215906464, 0.00023701080075112647, 0.0003858047280954123, 0.00017680245592464593]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 5.
Rec Success! in episode: 5.
total combined:  2
-----
It has processed 6 episodes
----target item:  873
[2.347191172963704e-05, 0.9980125441414079, 0.0002907349879343896, 0.00010153262866873617, 0.00034195741852686973, 0.00017696121091086457, 0.00030781781531488965, 0.00022033823655150423, 0.0003598337575988188, 0.00016480789135612568]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 6.
Rec Success! in episode: 6.
total combined:  2
-----
It has processed 7 episodes
----target item:  1241
[2.293367218316215e-05, 0.9981240150446794, 0.00027732548157193, 9.700705972525339e-05, 0.00032333001352156677, 0.00016677374763499354, 0.0002881899189213581, 0.00020613444698588325, 0.00033935758518736144, 0.00015493302958902188]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 7.
Rec Success! in episode: 7.
total combined:  2
-----
It has processed 8 episodes
----target item:  2000
[0.9981769612270724, 1.4328395534805842e-05, 0.00026844565859918633, 9.519124767206925e-05, 0.0003161640753449985, 0.00016421357810857774, 0.00028147409579918855, 0.0001999619469984448, 0.00033085418435913354, 0.00015240559051132014]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 8.
Rec Success! in episode: 8.
total combined:  2
-----
It has processed 9 episodes
----target item:  1177
[0.9979722186830138, 1.4963363996158556e-05, 0.00029913355358850586, 0.00010553662481194878, 0.00035150856604197533, 0.00018126112138180256, 0.0003130028596192448, 0.00022343172203821257, 0.00036999093095491705, 0.000168952574553466]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 9.
Rec Success! in episode: 9.
total combined:  2
-----
It has processed 10 episodes
----target item:  1
[2.5517024454027467e-05, 1.5308009879245577e-05, 0.9981959862956492, 0.00010762078583774842, 0.0003606908082069949, 0.00018586132403999758, 0.00032440336004687314, 0.00023299288676899526, 0.0003781532596968346, 0.00017346624542016037]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4995549687308346, 7.661012968943012e-06, 0.4995549687308346, 5.385966187209321e-05, 0.00018051052888322976, 9.301574960608234e-05, 0.00016235019235630814, 0.0001166031078689578, 0.00018924974896399136, 8.681253581103604e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331371849088899, 0.3331371849088899, 0.3331371849088899, 3.591728089863418e-05, 0.00012037668165197503, 6.202921983677952e-05, 0.00010826613573358084, 7.775887247359605e-05, 0.0001262045872043925, 5.789249553130437e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24990453988062483, 0.24990453988062483, 0.24990453988062483, 2.8659057067764195e-05, 9.565764779493444e-05, 4.9352281634640364e-05, 0.24990453988062483, 6.183156792084197e-05, 0.00010034848536451192, 4.599143771829692e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2109]
random_location_list [2109]
Random Combined Rec Success! in episode: 10.
Random Combined Rec Success! in episode: 10.
Rec Success! in episode: 10.
total combined:  3
-----
It has processed 11 episodes
----target item:  1691
[2.4273468453849177e-05, 0.9979939409999729, 0.0002955730268863723, 0.00010258474361583673, 0.000345156576062409, 0.0001789311987947359, 0.0003092352868293127, 0.0002220290529247229, 0.00036274778777497374, 0.00016552785868509414]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.4273468453849177e-05, 0.9979939409999729, 0.0002955730268863723, 0.00010258474361583673, 0.000345156576062409, 0.0001789311987947359, 0.0003092352868293127, 0.0002220290529247229, 0.00036274778777497374, 0.00016552785868509414]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.2677447819116576e-05, 0.4994982336494824, 0.0001557754395844097, 0.4994982336494824, 0.0001821156223396488, 9.418881441083151e-05, 0.00016331528491401703, 0.00011696126152197696, 0.00019133818413739925, 8.716064630808241e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.45533837163025e-06, 0.3331448602114861, 0.3331448602114861, 0.3331448602114861, 0.00012146365984798506, 6.282008082615486e-05, 0.0001089246049291522, 7.800837019023653e-05, 0.00012761473077060903, 5.81325806061316e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([7], dtype=torch.int32)
[6.342771452122847e-06, 0.24990859216950026, 0.24990859216950026, 0.24990859216950026, 9.111595542280089e-05, 4.712447897071684e-05, 8.170978430579102e-05, 0.24990859216950026, 9.573018081902e-05, 4.360815102846199e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.1999425093361149, 0.1999425093361149, 0.1999425093361149, 0.1999425093361149, 7.289846503331141e-05, 3.7702531532695414e-05, 6.537293963999377e-05, 0.1999425093361149, 7.659013404058084e-05, 3.48892491788567e-05]
[-1, 1, 0, 0, 1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 11.
Rec Success! in episode: 11.
total combined:  3
-----
It has processed 12 episodes
----target item:  2004
[0.9980362527942065, 1.479275168310819e-05, 0.0002910612376101746, 0.00010121127177293076, 0.0003398276053999737, 0.00017609312945681977, 0.00030272567427406833, 0.00021839135311071186, 0.0003548110012321251, 0.00016483318125357747]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 12.
Rec Success! in episode: 12.
total combined:  3
-----
It has processed 13 episodes
----target item:  1450
[0.998084491665484, 1.4983807286500547e-05, 0.00028348353285443956, 9.791571392053196e-05, 0.0003300077196086924, 0.00017302526943813849, 0.00029568461384224163, 0.0002133558114107374, 0.000347784587538669, 0.00015926727861612555]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 13.
Rec Success! in episode: 13.
total combined:  3
-----
It has processed 14 episodes
----target item:  1304
[0.9980987772305701, 1.441821337378131e-05, 0.0002803533562835797, 9.944897276179147e-05, 0.00032804641455246394, 0.00016882537407028042, 0.0002947942052559122, 0.00020989568148106454, 0.0003467497794280426, 0.00015869077222290505]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 14.
Rec Success! in episode: 14.
total combined:  3
-----
It has processed 15 episodes
----target item:  745
[0.9979410686508261, 1.4575251548753317e-05, 0.00030478550891727146, 0.00010560058942232744, 0.0003573824570273131, 0.00018456938848748384, 0.0003201502266400884, 0.00022731717704651478, 0.00037400917041819124, 0.00017054157966591652]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 15.
Rec Success! in episode: 15.
total combined:  3
-----
It has processed 16 episodes
----target item:  1864
[2.550830295876189e-05, 1.4644114406854628e-05, 0.0002790888079907708, 9.469712837962162e-05, 0.9984141442700935, 0.00016850623170068117, 0.00029419485695512346, 0.0002085809452851734, 0.00034445412574507473, 0.0001561812164843892]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.276605547209253e-05, 7.328891191225274e-06, 0.4996730033542168, 4.7392756621109024e-05, 0.4996730033542168, 8.433175287128489e-05, 0.00014723472077170772, 0.00010438781138191657, 0.00017238780972461033, 7.816349353235767e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 16.
Rec Success! in episode: 16.
total combined:  3
-----
It has processed 17 episodes
----target item:  1864
[2.280058491878035e-05, 0.9981166837057344, 0.0002777469216168634, 9.462663798359854e-05, 0.00032485790528920906, 0.00016793835594130398, 0.000291201258283589, 0.00020616479362870984, 0.0003426041793777052, 0.0001553756572258923]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 17.
Rec Success! in episode: 17.
total combined:  3
-----
It has processed 18 episodes
----target item:  157
[0.9980990392531375, 1.4403186247217917e-05, 0.00028296851955279833, 9.844645082977747e-05, 0.00032781906018470805, 0.00016856656647672367, 0.0002957882163394659, 0.00021133705874184922, 0.000344679109538438, 0.00015695257895143944]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 18.
Rec Success! in episode: 18.
total combined:  3
-----
It has processed 19 episodes
----target item:  95
[2.6003762951883628e-05, 1.5119429623716401e-05, 0.9982561521838613, 0.00010267883374570467, 0.00034678062562356395, 0.000181724192124882, 0.00031278272614127764, 0.00022295386829253633, 0.0003677958660404661, 0.00016800851159459943]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.499570158608971, 7.566410523664879e-06, 0.499570158608971, 5.138488868604354e-05, 0.00017354388627236232, 9.09425734910909e-05, 0.00015652988039863803, 0.00011157567033443293, 0.0001840608131806613, 8.407865917115066e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331439189054267, 0.3331439189054267, 0.3331439189054267, 3.426658477170349e-05, 0.00011572967155571462, 6.064606703596394e-05, 0.0001043836924267069, 7.440547724710603e-05, 0.0001227430012846728, 5.6068789398037984e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499130071578824, 0.2499130071578824, 0.2499130071578824, 2.5705602772109978e-05, 8.681638353450838e-05, 4.549457494242554e-05, 0.2499130071578824, 5.581640700192521e-05, 9.207754011966364e-05, 4.206086009975617e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2138]
random_location_list [2138]
Random Combined Rec Success! in episode: 19.
Random Combined Rec Success! in episode: 19.
Rec Success! in episode: 19.
total combined:  4
-----
It has processed 20 episodes
----target item:  1106
[0.9979447259918193, 1.5564640824144222e-05, 0.0003038791799760174, 0.00010580758000523382, 0.00035414973298984455, 0.00018406572433816166, 0.00031756828431703075, 0.0002283072219342172, 0.0003741113684467335, 0.00017182027534960444]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9979447259918193, 1.5564640824144222e-05, 0.0003038791799760174, 0.00010580758000523382, 0.00035414973298984455, 0.00018406572433816166, 0.00031756828431703075, 0.0002283072219342172, 0.0003741113684467335, 0.00017182027534960444]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995121062038061, 7.790738622970346e-06, 0.0001521039445049888, 0.4995121062038061, 0.00017726641008243874, 9.213241500194873e-05, 0.00015895590049346033, 0.00011427709202687395, 0.00018725802415749015, 8.600306749765056e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331502143922203, 5.196042719047407e-06, 0.3331502143922203, 0.3331502143922203, 0.000118228050511769, 6.144782764854311e-05, 0.00010601583359162485, 7.621724726194924e-05, 0.00012489196982400595, 5.7359851782131953e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 20.
Rec Success! in episode: 20.
total combined:  4
-----
It has processed 21 episodes
----target item:  1750
[2.6010200492238104e-05, 1.5250748133795269e-05, 0.9982302553104706, 0.00010609579414900776, 0.00035402405338514557, 0.0001826188603146553, 0.0003173207828970341, 0.0002267171215730639, 0.0003717410127918912, 0.000169966115792681]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49956367461101514, 7.632226871260543e-06, 0.49956367461101514, 5.309557038958666e-05, 0.00017717110463132888, 9.13914885135299e-05, 0.0001588029770598196, 0.00011346043435143722, 0.00018603754531180624, 8.505943084077788e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331410500782344, 0.3331410500782344, 0.3331410500782344, 3.540752655377256e-05, 0.00011814903853119391, 6.0945697213307596e-05, 0.00010589999477934733, 7.566268358403364e-05, 0.00012406174898006822, 5.67230756548064e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499116771657357, 0.2499116771657357, 0.2499116771657357, 2.6561585080150254e-05, 8.863160024234706e-05, 4.571949750124149e-05, 0.2499116771657357, 5.67597062832865e-05, 9.306712502839952e-05, 4.255182292174009e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 21.
Rec Success! in episode: 21.
total combined:  4
-----
It has processed 22 episodes
----target item:  289
[0.9980019797962675, 1.545027798507525e-05, 0.0002948930710243461, 0.00010269067240641343, 0.00034686639451616896, 0.0001781391503823663, 0.00030837131453266163, 0.000220737632224212, 0.0003629380993831039, 0.00016793359127830162]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 22.
Rec Success! in episode: 22.
total combined:  4
-----
It has processed 23 episodes
----target item:  505
[2.4874849004928158e-05, 1.426125187381702e-05, 0.0002968779172789912, 0.0001026893794781877, 0.00034482149413217743, 0.9981568616293932, 0.00030828903067293316, 0.00022117355691192594, 0.00036283765738078335, 0.000167313233872934]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2450746903048515e-05, 7.138263937455201e-06, 0.49961302081578945, 5.13996878236613e-05, 0.0001725954255770635, 0.49961302081578945, 0.00015430962789500304, 0.00011070523395787502, 0.00018161315624662277, 8.374622608039752e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33316406434337315, 4.760110178623962e-06, 0.33316406434337315, 3.427558567899196e-05, 0.00011509426511429978, 0.33316406434337315, 0.00010290048628610125, 7.382314742170951e-05, 0.00012110768685442691, 5.584568834656452e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499056664012124, 0.2499056664012124, 0.2499056664012124, 2.571004498123843e-05, 8.633196704162794e-05, 0.2499056664012124, 7.71854390989586e-05, 5.537458815859298e-05, 9.084262208565204e-05, 4.188973378443006e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2184]
random_location_list [2184]
Random Combined Rec Success! in episode: 23.
Random Combined Rec Success! in episode: 23.
Rec Success! in episode: 23.
total combined:  5
-----
It has processed 24 episodes
----target item:  765
[0.9980077860748152, 1.483504742771505e-05, 0.00029447758317672996, 0.00010344710788831298, 0.00034427371239408933, 0.0001767132050277571, 0.0003098436000444281, 0.00022093127005916457, 0.00036254313064487784, 0.00016514926852194138]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 24.
Rec Success! in episode: 24.
total combined:  5
-----
It has processed 25 episodes
----target item:  775
[0.9979566454421266, 1.4805800052278289e-05, 0.0003020592760252537, 0.00010490076836499803, 0.000353182495823469, 0.000182065043440305, 0.00031614459768831613, 0.00022724568845696835, 0.00037188901641499136, 0.0001710618716068599]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 25.
Rec Success! in episode: 25.
total combined:  5
-----
It has processed 26 episodes
----target item:  1174
[2.2958999892854962e-05, 0.9979991775367074, 0.0002936324580893325, 0.00010343854026784185, 0.0003445700324593229, 0.00017720254735947199, 0.0003096004297016609, 0.00022060691958108135, 0.0003638089797041602, 0.00016500355623679267]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 26.
Rec Success! in episode: 26.
total combined:  5
-----
It has processed 27 episodes
----target item:  1758
[0.9980482164393946, 1.4840188219220071e-05, 0.000286964044477532, 0.0001009112022189987, 0.0003376700301816703, 0.0001753312336596566, 0.0003022871723898669, 0.00021643043528058158, 0.00035376007458024964, 0.00016358917959782775]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 27.
Rec Success! in episode: 27.
total combined:  5
-----
It has processed 28 episodes
----target item:  1182
[2.5705289981659896e-05, 1.498786834264906e-05, 0.00030477072678354914, 0.00010879119027903805, 0.9982644095546758, 0.00018358176540320153, 0.0003209822797129913, 0.00022847896029680792, 0.0003759288797235354, 0.00017236348480071856]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2865770400016675e-05, 7.501587144894345e-06, 0.499641929774072, 5.445114514067996e-05, 0.499641929774072, 9.188462160872291e-05, 0.0001606550370063013, 0.0001143561440664766, 0.00018815639336141699, 8.626975312766381e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 28.
Rec Success! in episode: 28.
total combined:  5
-----
It has processed 29 episodes
----target item:  2019
[2.5529020054575417e-05, 1.5070022112038744e-05, 0.00029652231867718145, 0.00010524775825052051, 0.00034618453384041814, 0.00018081628783880486, 0.9982737312812308, 0.00022306352397857523, 0.0003659079431020384, 0.00016792731091511243]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2777433065831276e-05, 7.542639647958661e-06, 0.49964220152420197, 5.267715656534952e-05, 0.00017326750890225316, 9.049967488502706e-05, 0.49964220152420197, 0.00011164467891723378, 0.0001831391977148906, 8.404866189755408e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317711262368344, 5.029669014750058e-06, 0.33317711262368344, 3.5126782469792494e-05, 0.00011554021688208972, 6.0348025606309505e-05, 0.33317711262368344, 7.444817841240815e-05, 0.00012212296903008806, 5.604628753433038e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991305839923766, 0.24991305839923766, 0.24991305839923766, 2.6348273354136004e-05, 8.666564381247876e-05, 4.5266493634161626e-05, 0.24991305839923766, 5.58428873243512e-05, 9.160330507328855e-05, 4.2039799850981504e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 29.
Rec Success! in episode: 29.
total combined:  5
-----
It has processed 30 episodes
----target item:  2019
[0.9979533426662686, 1.515531021831093e-05, 0.0003008625866189556, 0.00010635987400645628, 0.0003522282176849559, 0.00018381295901040873, 0.00031877006068935704, 0.00022696485805119522, 0.00037253444026553567, 0.00016996902718609104]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9979533426662686, 1.515531021831093e-05, 0.0003008625866189556, 0.00010635987400645628, 0.0003522282176849559, 0.00018381295901040873, 0.00031877006068935704, 0.00022696485805119522, 0.00037253444026553567, 0.00016996902718609104]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995144028855971, 7.585821311064239e-06, 0.0001505934084093164, 0.4995144028855971, 0.00017630390150934845, 9.200552424365615e-05, 0.00015955679460687858, 0.00011360472549002781, 0.0001864679544901223, 8.507609874532848e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331509002206559, 5.059360018639728e-06, 0.3331509002206559, 0.3331509002206559, 0.0001175858056563495, 6.136304188623674e-05, 0.00010641633044518684, 7.576861917831708e-05, 0.0001243647160959165, 5.6741464751635964e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 30.
Rec Success! in episode: 30.
total combined:  5
-----
It has processed 31 episodes
----target item:  1650
[2.3172713812945253e-05, 0.9980075469167957, 0.0002922985208359485, 0.0001032425876209683, 0.00034414076222046773, 0.0001775849878162211, 0.0003061449313894473, 0.00021868976176390867, 0.00036063250669482607, 0.00016654631104969108]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 31.
Rec Success! in episode: 31.
total combined:  5
-----
It has processed 32 episodes
----target item:  1279
[0.9980805148288269, 1.4612627104250913e-05, 0.0002865089129147214, 0.00010033183070334044, 0.00033109903974467317, 0.00017144057604215842, 0.00029508679283635485, 0.0002113932249245913, 0.0003489710484140772, 0.00016004111848886716]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2207]
random_location_list [2207]
Random Combined Rec Success! in episode: 32.
Random Combined Rec Success! in episode: 32.
Rec Success! in episode: 32.
total combined:  6
-----
It has processed 33 episodes
----target item:  984
[0.9981374647919761, 1.3954647143436165e-05, 0.00027599299843142144, 9.427053128360244e-05, 0.00032108291390294235, 0.00016747607514636546, 0.00028950505547035396, 0.00020756860737097054, 0.00033889700625127934, 0.00015378737302376507]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 33.
Rec Success! in episode: 33.
total combined:  6
-----
It has processed 34 episodes
----target item:  914
[2.523447149198313e-05, 1.502986344145484e-05, 0.00029039674658898335, 0.00010019392787015265, 0.9983487073863145, 0.00017549382641739202, 0.000305799050960941, 0.00021877835166192718, 0.0003580389834962234, 0.000162327391756407]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.262949702599206e-05, 7.522234642212556e-06, 0.4996594454076116, 5.014564757025195e-05, 0.4996594454076116, 8.783218461787712e-05, 0.0001530481114252528, 0.00010949547893418594, 0.00017919346076621196, 8.124256979488955e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 34.
Rec Success! in episode: 34.
total combined:  6
-----
It has processed 35 episodes
----target item:  1951
[0.9981317335225478, 1.478571713829042e-05, 0.0002769449653010149, 9.712307047460568e-05, 0.0003227741064323572, 0.00016765976707043719, 0.00029006351394471384, 0.00020696806314398405, 0.000337878439021498, 0.00015406883492542506]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 35.
Rec Success! in episode: 35.
total combined:  6
-----
It has processed 36 episodes
----target item:  1590
[0.9980327907418032, 1.5022561343528571e-05, 0.000290550607986573, 0.00010120082482485851, 0.00033820535101688364, 0.0001768858968346983, 0.00030574394572921703, 0.00021656337407196158, 0.00035775727203461234, 0.00016527942435458348]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 36.
Rec Success! in episode: 36.
total combined:  6
-----
It has processed 37 episodes
----target item:  1273
[2.3846876164873592e-05, 0.997961076591702, 0.0002992399346981418, 0.0001035368138441388, 0.00035168269660174083, 0.00018308829522480107, 0.0003136964119668549, 0.00022506608045561743, 0.00036923640190937454, 0.00016952989743248786]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 37.
Rec Success! in episode: 37.
total combined:  6
-----
It has processed 38 episodes
----target item:  702
[2.3558066892524743e-05, 0.998075547772385, 0.00028255156253626385, 9.925873799846096e-05, 0.0003306074940505193, 0.00017294517863215058, 0.0002968994206871805, 0.00021135173334270327, 0.00034858400728805474, 0.00015869602618716653]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 38.
Rec Success! in episode: 38.
total combined:  6
-----
It has processed 39 episodes
----target item:  1154
[0.9979922729110822, 1.453191933752546e-05, 0.00029981534117834246, 0.00010525037600609725, 0.00034683150394383504, 0.0001795060480470952, 0.0003092474691528559, 0.0002223760196833039, 0.00036577358663489985, 0.0001643948249337167]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 39.
Rec Success! in episode: 39.
total combined:  6
-----
It has processed 40 episodes
----target item:  985
[2.5805408427243263e-05, 1.5428188014280524e-05, 0.00030972848131407323, 0.00010848519373607607, 0.9982472904320725, 0.0001848159488226252, 0.00032238568497170827, 0.00023137644747770549, 0.0003799302559594087, 0.00017475395920423976]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.291602346273886e-05, 7.722057139371593e-06, 0.49963888233694254, 5.429859060768278e-05, 0.49963888233694254, 9.250336564180391e-05, 0.00016135923920311876, 0.00011580764678741652, 0.00019016122585354978, 8.746717741950478e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 40.
Rec Success! in episode: 40.
total combined:  6
-----
It has processed 41 episodes
----target item:  841
[0.9979323195239557, 1.5255305486392261e-05, 0.00030768242936680636, 0.00010846113368158284, 0.00035674627853169485, 0.00018511295986550706, 0.0003182970927845029, 0.00022940191403976869, 0.00037623575738100984, 0.0001704876049068161]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 41.
Rec Success! in episode: 41.
total combined:  6
-----
It has processed 42 episodes
----target item:  212
[2.4652697837749707e-05, 1.4287849644720657e-05, 0.0002809542548788553, 0.9981821706828071, 0.0003267795378131066, 0.0001683990032585131, 0.00029242783293738074, 0.00020818622153133412, 0.0003428332289555116, 0.00015930869033553934]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49955129247739105, 7.15051216739367e-06, 0.00014060666006060526, 0.49955129247739105, 0.00016354042905618654, 8.427714118771485e-05, 0.00014634873892838937, 0.00010418909403162487, 0.0001715746761052351, 7.972779368074709e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33316636347207246, 4.768899954114674e-06, 9.377497429749099e-05, 0.33316636347207246, 0.00010907022131621867, 5.6207058366492275e-05, 0.33316636347207246, 6.948696178888836e-05, 0.00011442851167173583, 5.317295638759332e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 42.
Rec Success! in episode: 42.
total combined:  6
-----
It has processed 43 episodes
----target item:  917
[0.9980676376966913, 1.4272898191450605e-05, 0.00028595503062013534, 0.00010000924551897133, 0.00033297175240673186, 0.00017271977405160246, 0.00030069911768456134, 0.0002123950876817954, 0.0003512450945938082, 0.00016209430255976345]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 43.
Rec Success! in episode: 43.
total combined:  6
-----
It has processed 44 episodes
----target item:  1765
[0.998124812263379, 1.468276672846816e-05, 0.0002766052613597394, 9.758939227306846e-05, 0.00032717855648358026, 0.00016659923695613993, 0.00028833453661109763, 0.00020573883102938025, 0.0003411181110223489, 0.00015734104415727899]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 44.
Rec Success! in episode: 44.
total combined:  6
-----
It has processed 45 episodes
----target item:  1336
[2.4423821683815305e-05, 1.4109802653558427e-05, 0.00028695785371258653, 0.00010044553720284092, 0.9983766584675902, 0.00017269997847667326, 0.00029961775862338293, 0.00021360116996782343, 0.000352564788048194, 0.00015892082204087914]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2223586196511357e-05, 7.061646256033171e-06, 0.4996655846636198, 5.0270784726021466e-05, 0.4996655846636198, 8.643254525740975e-05, 0.0001499521060197301, 0.00010690269305837385, 0.00017645093107675533, 7.953638016954571e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2223586196511357e-05, 7.061646256033171e-06, 0.4996655846636198, 5.0270784726021466e-05, 0.4996655846636198, 8.643254525740975e-05, 0.0001499521060197301, 0.00010690269305837385, 0.00017645093107675533, 7.953638016954571e-05]
[0, -1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 45.
Rec Success! in episode: 45.
total combined:  6
-----
It has processed 46 episodes
----target item:  1133
[0.997973153367012, 1.4320923697185451e-05, 0.000298872811884505, 0.00010404938303973764, 0.0003486376547169606, 0.00018115484567441726, 0.00031789532092856454, 0.0002262793239232914, 0.0003690434518532732, 0.00016659291727012297]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 46.
Rec Success! in episode: 46.
total combined:  6
-----
It has processed 47 episodes
----target item:  1977
[2.3359789362388406e-05, 0.9980344766524389, 0.0002887923630366669, 0.00010154630876129354, 0.00033862226677224195, 0.00017370322737849547, 0.0003025611540158575, 0.0002151771986720309, 0.0003567157915089015, 0.00016504524805349469]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 47.
Rec Success! in episode: 47.
total combined:  6
-----
It has processed 48 episodes
----target item:  1977
[2.3359789362388406e-05, 0.9980344766524389, 0.0002887923630366669, 0.00010154630876129354, 0.00033862226677224195, 0.00017370322737849547, 0.0003025611540158575, 0.0002151771986720309, 0.0003567157915089015, 0.00016504524805349469]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 48.
Rec Success! in episode: 48.
total combined:  6
-----
It has processed 49 episodes
----target item:  1977
[2.6335337244635373e-05, 1.5609733380953255e-05, 0.0002935419642286288, 0.00010331158715205419, 0.00034427097685101586, 0.00017688045296256448, 0.00030713250310910857, 0.9982027273833645, 0.00036270291384731413, 0.0001674871478592741]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3181448604787588e-05, 7.813034493696737e-06, 0.4996236739228737, 5.170985143170096e-05, 0.0001723156284397342, 8.853277929419861e-05, 0.00015372695883805957, 0.4996236739228737, 0.0001815412414609945, 8.383121168950302e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331689638277498, 5.2100425629896006e-06, 0.3331689638277498, 3.44821883357076e-05, 0.00011490692370084955, 5.9037183147555035e-05, 0.0001025112584964774, 0.3331689638277498, 0.00012105892988349405, 5.590199062370287e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990850739963438, 0.24990850739963438, 0.24990850739963438, 2.5864930874248566e-05, 8.619115496847248e-05, 4.428351954509237e-05, 7.689322351093193e-05, 0.24990850739963438, 9.080574651071732e-05, 4.19318260528634e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 49.
Rec Success! in episode: 49.
total combined:  6
-----
It has processed 50 episodes
----target item:  1977
[0.9980226601364636, 1.5125759498522239e-05, 0.00029126220720779636, 0.00010250148403339956, 0.00034226676231026426, 0.0001752864834219896, 0.00030554115700908157, 0.00021792310370295884, 0.0003608265580025762, 0.0001666063483498736]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 50.
Rec Success! in episode: 50.
total combined:  6
-----
It has processed 51 episodes
----target item:  1977
[2.4016026722543793e-05, 0.9979815650768987, 0.0002962310992967011, 0.00010467931880777364, 0.0003480124387165207, 0.00017830625028093685, 0.0003099120344545508, 0.00022134741674923776, 0.00036657609296452266, 0.00016935424510874258]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 51.
Rec Success! in episode: 51.
total combined:  6
-----
It has processed 52 episodes
----target item:  1977
[2.6912919408612505e-05, 1.5902738181925936e-05, 0.00029966723047756503, 0.00010580277677518957, 0.00035120168210962376, 0.00017988127657039038, 0.00031255920674533116, 0.9981679382607378, 0.00036994983246389215, 0.00017018407652975403]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3470817770550034e-05, 7.959853215810478e-06, 0.49961649260589275, 5.295783426233062e-05, 0.00017578820746200454, 9.003660510491476e-05, 0.00015644635398516572, 0.49961649260589275, 0.00018517228479389007, 8.518283161982124e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33316583478883066, 5.307973577113209e-06, 0.33316583478883066, 3.531456891783524e-05, 0.00011722316166874298, 6.0040293195432066e-05, 0.00010432517920550704, 0.33316583478883066, 0.00012348086933906761, 5.680358760430442e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990676523008098, 0.24990676523008098, 0.24990676523008098, 2.6489359838906373e-05, 8.792876724963782e-05, 4.503605678969545e-05, 7.825402650851529e-05, 0.24990676523008098, 9.26226563533555e-05, 4.260821293591761e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 52.
Rec Success! in episode: 52.
total combined:  6
-----
It has processed 53 episodes
----target item:  1977
[2.3359789362388406e-05, 0.9980344766524389, 0.0002887923630366669, 0.00010154630876129354, 0.00033862226677224195, 0.00017370322737849547, 0.0003025611540158575, 0.0002151771986720309, 0.0003567157915089015, 0.00016504524805349469]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 53.
Rec Success! in episode: 53.
total combined:  6
-----
It has processed 54 episodes
----target item:  1764
[2.4654884314867533e-05, 1.5033358534648944e-05, 0.0002913574555968746, 0.00010210489023843139, 0.9983389661285166, 0.0001767866031399156, 0.000304779506825437, 0.00021808339450073, 0.00036115861796103286, 0.00016707516037145823]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2339487912023794e-05, 7.524024187108299e-06, 0.49965724630135416, 5.110233099312799e-05, 0.49965724630135416, 8.847967504504824e-05, 0.00015253866099210125, 0.00010914824729605845, 0.00018075576197151296, 8.361920889484093e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318370504325806, 5.01720384133862e-06, 0.33318370504325806, 3.407628750042838e-05, 0.33318370504325806, 5.9000417127449495e-05, 0.00010171651989018307, 7.278272796457182e-05, 0.00012053237479770881, 5.5759339104162515e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991676515863304, 0.24991676515863304, 0.24991676515863304, 2.5560180200340045e-05, 0.24991676515863304, 4.425544577453985e-05, 7.62962390698185e-05, 5.4593377938350765e-05, 9.040976719560875e-05, 4.1824355289182966e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 54.
Rec Success! in episode: 54.
total combined:  6
-----
It has processed 55 episodes
----target item:  1252
[2.4468400367314e-05, 1.4589415814832118e-05, 0.00028945783981827706, 0.00010062234156988266, 0.0003394869693000459, 0.0001744193443432613, 0.9983204651682521, 0.00021588028297572345, 0.00035750361011068616, 0.00016310662744794594]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2246256578385479e-05, 7.30189659786092e-06, 0.49965213828343225, 5.036075075953137e-05, 0.0001699107611718067, 8.729561438412175e-05, 0.49965213828343225, 0.00010804651288389005, 0.00017892795897532342, 8.163368178456635e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331814130445158, 4.869099999728579e-06, 0.3331814130445158, 3.358189591200177e-05, 0.00011330104118673587, 5.8211051098498366e-05, 0.3331814130445158, 7.204830536873667e-05, 0.00011931394991999812, 5.4435522966939424e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991544785113026, 0.24991544785113026, 0.24991544785113026, 2.5189384005093452e-05, 8.498577454078821e-05, 4.366342279490403e-05, 0.24991544785113026, 5.404258400433961e-05, 8.949598645576208e-05, 4.0831443678028666e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 55.
Rec Success! in episode: 55.
total combined:  6
-----
It has processed 56 episodes
----target item:  531
[2.5064465133543358e-05, 1.4598102539350056e-05, 0.9983131925455837, 0.0001021335092063544, 0.00033498925020767674, 0.00017506281258230195, 0.0003011318099048201, 0.00021611563865638614, 0.0003547276385050052, 0.00016298422768098333]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49958420836166423, 7.305304142187418e-06, 0.49958420836166423, 5.11105019196924e-05, 0.0001676381125926352, 8.760639175215777e-05, 0.00015069489012782474, 0.00010815038913531762, 0.00017751576137609119, 8.156192562558309e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331501087693805, 0.3331501087693805, 0.3331501087693805, 3.4083281634627754e-05, 0.00011179027381045545, 5.8420739592304385e-05, 0.0001004916052124899, 7.212060209436896e-05, 0.0001183772309470426, 5.4389958567169566e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991576043365857, 0.24991576043365857, 0.24991576043365857, 2.556790174632361e-05, 8.386054980329229e-05, 4.382488006454281e-05, 0.24991576043365857, 5.410196377220603e-05, 8.880181909422819e-05, 4.080115088504716e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 56.
Rec Success! in episode: 56.
total combined:  6
-----
It has processed 57 episodes
----target item:  977
[2.639807775204928e-05, 1.5061616386836542e-05, 0.00030401183534212243, 0.00010486137821633976, 0.9982763906374258, 0.00018432950386277762, 0.00031666266215718726, 0.00022655870956499947, 0.00037345335199502383, 0.0001722722272970877]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3212433781430287e-05, 7.538450754693104e-06, 0.4996447404522972, 5.248389784007479e-05, 0.4996447404522972, 9.225828435791257e-05, 0.00015849201196016906, 0.00011339431514105135, 0.00018691617359541967, 8.622352797508455e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 57.
Rec Success! in episode: 57.
total combined:  6
-----
It has processed 58 episodes
----target item:  1968
[2.4446297759805882e-05, 1.4461437536524673e-05, 0.0002855062110719669, 0.9981409750644843, 0.0003354242474872048, 0.00017287123901674854, 0.00029970909688655737, 0.00021209974894061974, 0.0003541508951781583, 0.00016035576163815437]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49954092301141007, 7.237534612383467e-06, 0.00014288766794206281, 0.49954092301141007, 0.00016787021310225335, 8.651709573887963e-05, 0.0001499958048350381, 0.00010614983955491912, 0.00017724236303512636, 8.025345835917237e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331625621758795, 4.8269830642948345e-06, 9.529714055844544e-05, 0.3331625621758795, 0.00011195893616283395, 5.770149343244622e-05, 0.3331625621758795, 7.079530603315074e-05, 0.0001182095741804547, 5.3524038930052586e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.2499217938316503, 3.620959865192503e-06, 0.2499217938316503, 0.2499217938316503, 8.398596162352505e-05, 4.3284757600673176e-05, 0.2499217938316503, 5.310707710707677e-05, 8.867487581530449e-05, 4.015104138697338e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.19996338105467215, 2.8971438072939572e-06, 0.19996338105467215, 0.19996338105467215, 0.19996338105467215, 3.463229974970836e-05, 0.19996338105467215, 4.249117507301354e-05, 7.094910656161393e-05, 3.2125001447506836e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.1666471371081277, 2.414445678651914e-06, 0.1666471371081277, 0.1666471371081277, 0.1666471371081277, 2.886215253172514e-05, 0.1666471371081277, 0.1666471371081277, 5.912815349746349e-05, 2.6772599525898975e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 58.
Rec Success! in episode: 58.
total combined:  6
-----
It has processed 59 episodes
----target item:  1777
[2.398684799838706e-05, 0.9980351655654794, 0.0002900827959505968, 0.00010107985383847398, 0.00033891611737137746, 0.0001734388011289975, 0.0003024900866040596, 0.0002165650859347247, 0.0003553448739325817, 0.0001629299717613518]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 59.
Rec Success! in episode: 59.
total combined:  6
-----
It has processed 60 episodes
----target item:  201
[0.9980565526272948, 1.460140172634472e-05, 0.0002870189274658331, 0.00010057492371328409, 0.0003367646502588394, 0.0001749493590430788, 0.0002990776552345796, 0.0002140369857173978, 0.0003541234431405075, 0.00016230002640553375]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 60.
Rec Success! in episode: 60.
total combined:  6
-----
It has processed 61 episodes
----target item:  1973
[0.9980190019154949, 1.5145795218989772e-05, 0.00029293010834646386, 0.00010247229642305361, 0.00034279032204041174, 0.00017755643302107702, 0.0003051344134462414, 0.00021950562660270822, 0.0003605643375141311, 0.00016489875189242285]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 61.
Rec Success! in episode: 61.
total combined:  6
-----
It has processed 62 episodes
----target item:  1973
[2.664096594376517e-05, 1.558757438851043e-05, 0.00030234062671268686, 0.0001061405300333776, 0.0003534697411138597, 0.0001831415954475662, 0.9982437428747626, 0.0002266816560795562, 0.00037208842895279415, 0.00017016600656523032]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3334207857041859e-05, 7.80181759633769e-06, 0.49963614636122755, 5.3124946464370834e-05, 0.0001769169709963173, 9.166514855816013e-05, 0.49963614636122755, 0.00011345760983004701, 0.0001862359068860211, 8.517066935685023e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317454383331185, 5.202519949089555e-06, 0.33317454383331185, 3.5425539031435854e-05, 0.00011797431298225911, 6.112546956159884e-05, 0.33317454383331185, 7.56574312624176e-05, 0.0001241884995191539, 5.679472775860893e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991164551165504, 0.24991164551165504, 0.24991164551165504, 2.657242252251062e-05, 8.84916186761672e-05, 4.584974141498145e-05, 0.24991164551165504, 5.6750053363726595e-05, 9.315283188016491e-05, 4.260128552210628e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 62.
Rec Success! in episode: 62.
total combined:  6
-----
It has processed 63 episodes
----target item:  1973
[2.6592273854550357e-05, 1.5616060409011724e-05, 0.0003006452524323346, 0.00010535545408100932, 0.00035223472006710223, 0.0001826054361704482, 0.9982515121391388, 0.00022549273178731644, 0.0003707075149665577, 0.00016923841709309134]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3309773676260409e-05, 7.816038255908337e-06, 0.4996376681147606, 5.2731754232364444e-05, 0.0001762979890571431, 9.139635973881173e-05, 0.4996376681147606, 0.00011286200052491227, 0.0001855438595165306, 8.470599547665851e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331752150701728, 5.211997399505167e-06, 0.3331752150701728, 3.516330869064931e-05, 0.00011756143335266148, 6.094616910591948e-05, 0.3331752150701728, 7.52601809227496e-05, 0.0001237268909940774, 5.6484809016013886e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499120249497437, 0.2499120249497437, 0.2499120249497437, 2.6375712481981088e-05, 8.81818770912176e-05, 4.571522683937304e-05, 0.2499120249497437, 5.6452050938203865e-05, 9.280653683243994e-05, 4.236879684198128e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 63.
Rec Success! in episode: 63.
total combined:  6
-----
It has processed 64 episodes
----target item:  179
[2.2896384495363746e-05, 0.9981297861631272, 0.0002747406075354347, 9.581802235939318e-05, 0.00032034892938940466, 0.00016689811775043634, 0.0002891835097718808, 0.00020664067128023302, 0.0003373197542696233, 0.00015636784002098932]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2156]
random_location_list [2156]
Random Combined Rec Success! in episode: 64.
Random Combined Rec Success! in episode: 64.
Rec Success! in episode: 64.
total combined:  7
-----
It has processed 65 episodes
----target item:  824
[0.997920573756715, 1.5220180168113706e-05, 0.00030862177076554646, 0.00010683699242592886, 0.0003601059001894624, 0.0001848732525335335, 0.00032114991557239173, 0.00022929526208285847, 0.00038015025753920675, 0.00017317271200806321]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 65.
Rec Success! in episode: 65.
total combined:  7
-----
It has processed 66 episodes
----target item:  230
[2.2630869572441585e-05, 0.9980097611836738, 0.0002947915994877904, 0.0001018434812099001, 0.0003429559388437256, 0.0001773973788135466, 0.00030714774946799083, 0.00021922284737582438, 0.0003598246505073177, 0.00016442430104755191]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2630869572441585e-05, 0.9980097611836738, 0.0002947915994877904, 0.0001018434812099001, 0.0003429559388437256, 0.0001773973788135466, 0.00030714774946799083, 0.00021922284737582438, 0.0003598246505073177, 0.00016442430104755191]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1327283590960706e-05, 0.4995274068143022, 0.00014755014326525733, 0.4995274068143022, 0.00017165753026201282, 8.879156904165457e-05, 0.00015373468754315863, 0.00010972620181010362, 0.00018010071801562592, 8.229823786705603e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.554645702730622e-06, 0.3331560075265825, 0.3331560075265825, 0.3331560075265825, 0.00011448568519729979, 5.921886214931016e-05, 0.00010253218146099712, 7.318105636934503e-05, 0.0001201168051006703, 5.488818427224757e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990165709351111, 0.24990165709351111, 0.24990165709351111, 0.24990165709351111, 8.587617151705861e-05, 4.442030594667878e-05, 7.69098004347747e-05, 5.489340381500929e-05, 9.01000971355461e-05, 4.117184710647672e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 66.
Rec Success! in episode: 66.
total combined:  7
-----
It has processed 67 episodes
----target item:  1783
[0.998040949594431, 1.4256233855827786e-05, 0.00029004504513736905, 9.94729480477345e-05, 0.000339192718359819, 0.00017457725526500264, 0.0003060283157202393, 0.00021678638497416144, 0.0003557563186705254, 0.0001629351855381772]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 67.
Rec Success! in episode: 67.
total combined:  7
-----
It has processed 68 episodes
----target item:  1935
[2.3653903814916743e-05, 0.9979197676029941, 0.0003068759036319498, 0.0001087502049978857, 0.0003574086544980866, 0.000184080494591394, 0.0003212549402918838, 0.00022953253721385376, 0.00037593896491050423, 0.00017273679305527528]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 68.
Rec Success! in episode: 68.
total combined:  7
-----
It has processed 69 episodes
----target item:  1170
[2.5433066739206303e-05, 1.4887632485878001e-05, 0.00030566831671640396, 0.00010731630883250453, 0.9982740894657437, 0.00018262554661025243, 0.0003178978282198385, 0.00022757798649303062, 0.00037354589871345937, 0.00017095794944561597]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2729463824348037e-05, 7.4513852813129835e-06, 0.4996445784121245, 5.3712715224391367e-05, 0.4996445784121245, 9.140562216955606e-05, 0.0001591105369107967, 0.00011390469643266486, 0.00018696286425720082, 8.55658916507291e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 69.
Rec Success! in episode: 69.
total combined:  7
-----
It has processed 70 episodes
----target item:  984
[2.4075213205387565e-05, 0.9978894870846692, 0.0003109797276053702, 0.00010950397909360046, 0.0003626979118202076, 0.00018870277117980446, 0.0003234744730808812, 0.00023171779277370174, 0.0003826134151595988, 0.0001767476314121688]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 70.
Rec Success! in episode: 70.
total combined:  7
-----
It has processed 71 episodes
----target item:  1133
[2.3667680482899693e-05, 0.9980507774044004, 0.000285027428574195, 0.00010110650852448744, 0.0003344711924250469, 0.00017384186130988473, 0.00030111365260837493, 0.00021502446583450066, 0.00035252506362883914, 0.00016244474221136467]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 71.
Rec Success! in episode: 71.
total combined:  7
-----
It has processed 72 episodes
----target item:  1388
[2.4968117532243695e-05, 1.4566177888753897e-05, 0.0002998932694393919, 0.9980477246622396, 0.0003515105498178482, 0.0001804387906003211, 0.0003152016231106407, 0.0002261636718518747, 0.0003702595424420755, 0.0001692735950773676]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.499517696379104, 7.290296289689915e-06, 0.00015009502191957717, 0.499517696379104, 0.0001759292023408858, 9.03086764198642e-05, 0.00015775677332911686, 0.00011319374171843377, 0.00018531297565518523, 8.472055411926434e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33315395668797293, 4.862272291739864e-06, 0.00010010606389753317, 0.33315395668797293, 0.00011733620306485091, 6.023148547213351e-05, 0.33315395668797293, 7.549470859425235e-05, 0.00012359472249465954, 5.6504480266119306e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991785330502989, 3.647468772145678e-06, 0.24991785330502989, 0.24991785330502989, 8.802060247597605e-05, 4.5183085022361145e-05, 0.24991785330502989, 5.663290238343271e-05, 9.271547615034314e-05, 4.2387245076158375e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.199948006141607, 0.199948006141607, 0.199948006141607, 0.199948006141607, 7.042131537107036e-05, 3.614894911297636e-05, 0.199948006141607, 4.5309431734590416e-05, 7.417747211562545e-05, 3.3912123630756806e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664033787293653, 0.16664033787293653, 0.16664033787293653, 0.16664033787293653, 0.16664033787293653, 3.0127197615922952e-05, 0.16664033787293653, 3.776171195093377e-05, 6.182086660646111e-05, 2.826298620760375e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 72.
Rec Success! in episode: 72.
total combined:  7
-----
It has processed 73 episodes
----target item:  211
[2.3067808692989477e-05, 0.9980667264698437, 0.00028427965646493896, 9.937254270891322e-05, 0.00033404968211367777, 0.00017232486501372676, 0.00029740588999448614, 0.00021226427541307094, 0.0003499790295741766, 0.0001605297801801865]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 73.
Rec Success! in episode: 73.
total combined:  7
-----
It has processed 74 episodes
----target item:  1450
[2.6390735482583873e-05, 1.56602489088904e-05, 0.00030055975406415237, 0.00010483611009894417, 0.9982882548779373, 0.0001827226486053888, 0.00031482931121298174, 0.00022670012825390788, 0.00037038400080586126, 0.00016966218463024924]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3208657664404521e-05, 7.838010688008506e-06, 0.4996468483335902, 5.2470848721840824e-05, 0.4996468483335902, 9.145334030401032e-05, 0.00015757319826409776, 0.00011346422643501452, 0.0001853785194522421, 8.491653129011406e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 74.
Rec Success! in episode: 74.
total combined:  7
-----
It has processed 75 episodes
----target item:  2013
[2.6529051049215473e-05, 1.5431828718472106e-05, 0.0003028713936205747, 0.00010582585165448364, 0.00035263281818316095, 0.00018097569971194322, 0.9982498839953593, 0.00022619218308785632, 0.000370914529094808, 0.00016874264952012276]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3278155467531236e-05, 7.723842835239503e-06, 0.4996378170687482, 5.2967296423280307e-05, 0.0001764975827481833, 9.058083050774984e-05, 0.4996378170687482, 0.00011321230325988851, 0.00018564783087605559, 8.445802038582849e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331752742795315, 5.150517769492268e-06, 0.3331752742795315, 3.532037189899789e-05, 0.00011769451497245051, 6.040233949051689e-05, 0.3331752742795315, 7.549376548741264e-05, 0.00012379620768981767, 5.631944409700839e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991204673820752, 0.24991204673820752, 0.24991204673820752, 2.649352192152008e-05, 8.828169254225091e-05, 4.5307300556722344e-05, 0.24991204673820752, 5.662725569816578e-05, 9.285852231709634e-05, 4.224475413392378e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 75.
Rec Success! in episode: 75.
total combined:  7
-----
It has processed 76 episodes
----target item:  984
[0.9980982904091662, 1.439555375629288e-05, 0.0002814216151926896, 9.740995703791387e-05, 0.00032966822518924423, 0.0001696637450267587, 0.00029460124168764025, 0.00021217720281215894, 0.000344208550159734, 0.00015816349997131832]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 76.
Rec Success! in episode: 76.
total combined:  7
-----
It has processed 77 episodes
----target item:  786
[0.9980020408184541, 1.4403135972185784e-05, 0.0002971853836947846, 0.00010298230747898246, 0.00034469733436997164, 0.00018034381159367653, 0.00030893004893377116, 0.00022118077573075472, 0.0003627205472009679, 0.00016551583657083122]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2197]
random_location_list [2197]
Random Combined Rec Success! in episode: 77.
Random Combined Rec Success! in episode: 77.
Rec Success! in episode: 77.
total combined:  8
-----
It has processed 78 episodes
----target item:  950
[0.9980402363670752, 1.4570419709678297e-05, 0.0002904671402954593, 0.00010066669240676453, 0.0003384676082107965, 0.00017680710164157134, 0.0003030239002316594, 0.00021807460735834652, 0.0003558014519548379, 0.00016188471111571023]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 78.
Rec Success! in episode: 78.
total combined:  8
-----
It has processed 79 episodes
----target item:  1254
[2.4735263431322278e-05, 1.4074438889238516e-05, 0.0002832727253485948, 9.756746682365617e-05, 0.0003291963633552669, 0.9982414219994783, 0.0002957949973936948, 0.0002109973830884498, 0.0003459185206730223, 0.00015702084151835612]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[1.2380348642639246e-05, 7.044455414113144e-06, 0.00014178199922970135, 4.883389492939107e-05, 0.00016476742855571383, 0.4996339282252332, 0.4996339282252332, 0.0001056071698032399, 0.00017313710443265295, 7.85911485258814e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[8.256361111192694e-06, 4.697894171598684e-06, 0.3332020974452829, 3.256695612064301e-05, 0.00010988215508191136, 0.3332020974452829, 0.3332020974452829, 7.042862483077173e-05, 0.00011546382878257352, 5.241184405245705e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[5.716527832631163e-06, 0.24992717229076084, 0.24992717229076084, 2.442771914029205e-05, 8.242005832315251e-05, 0.24992717229076084, 0.24992717229076084, 5.282687950417892e-05, 8.660674242674007e-05, 3.931290972958539e-05]
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.199954302039091, 0.199954302039091, 0.199954302039091, 1.954340332959709e-05, 6.594019003605701e-05, 0.199954302039091, 0.199954302039091, 4.226415928826056e-05, 6.928974778969369e-05, 3.145230410145215e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 79.
Rec Success! in episode: 79.
total combined:  8
-----
It has processed 80 episodes
----target item:  995
[2.250423429792401e-05, 0.9981370711676922, 0.0002750832561595234, 9.586266537893072e-05, 0.00031937418532342537, 0.0001660823220956622, 0.0002878229108879053, 0.00020518754382490577, 0.00033704336462127196, 0.00015396834971827684]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.250423429792401e-05, 0.9981370711676922, 0.0002750832561595234, 9.586266537893072e-05, 0.00031937418532342537, 0.0001660823220956622, 0.0002878229108879053, 0.00020518754382490577, 0.00033704336462127196, 0.00015396834971827684]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1263148228455547e-05, 0.49955780036982983, 0.0001376764678270673, 0.49955780036982983, 0.00015984364284599568, 8.31225709404431e-05, 0.00014405253988913016, 0.00010269435032258907, 0.00016868689353705175, 7.705964674957232e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.511669377322342e-06, 0.3331673307610478, 0.3331673307610478, 0.3331673307610478, 0.0001066036398324627, 5.543647815272067e-05, 9.607216656146797e-05, 6.848937711689725e-05, 0.00011250142028110901, 5.139296553459403e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990802002122042, 0.24990802002122042, 0.24990802002122042, 0.24990802002122042, 7.996313593151612e-05, 4.1582770016644755e-05, 7.206350295415096e-05, 5.137371839151401e-05, 8.438704697667849e-05, 3.8549740847732634e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 80.
Rec Success! in episode: 80.
total combined:  8
-----
It has processed 81 episodes
----target item:  1587
[2.657819312717421e-05, 1.5830445153277964e-05, 0.0003072395916770297, 0.00010521445237107207, 0.9982587770502936, 0.00018535229117977865, 0.00032145291226251587, 0.00022791122296533708, 0.00037804191558557304, 0.00017360192538450967]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3302721627062851e-05, 7.923337907091683e-06, 0.49964113660137793, 5.266116339583706e-05, 0.49964113660137793, 9.27711647178118e-05, 0.0001608912459765677, 0.00011407244805108682, 0.00018921475746425776, 8.688995810445451e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 81.
Rec Success! in episode: 81.
total combined:  8
-----
It has processed 82 episodes
----target item:  455
[2.36849825851674e-05, 0.997981870330424, 0.0002969944387612144, 0.00010369252237431321, 0.0003495747470848258, 0.0001797718905523181, 0.0003097506853093933, 0.00022224654798805803, 0.00036478775867318085, 0.00016762609624759123]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 82.
Rec Success! in episode: 82.
total combined:  8
-----
It has processed 83 episodes
----target item:  1471
[0.9980752757483238, 1.5007315326200888e-05, 0.00028596684615727903, 9.918304656335478e-05, 0.0003333959651552251, 0.0001726781271273452, 0.0002977546892694919, 0.00021263508072732855, 0.00034822419881827245, 0.000159878982531934]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 83.
Rec Success! in episode: 83.
total combined:  8
-----
It has processed 84 episodes
----target item:  1467
[2.6116701366613647e-05, 1.530895112118681e-05, 0.00031262715945405565, 0.000106784792510119, 0.00036086043071052856, 0.0001876712741106193, 0.9982027141961094, 0.0002317043877673155, 0.00038242165133221275, 0.00017379045551806356]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([7], dtype=torch.int32)
[1.3071611769341398e-05, 7.662248874499606e-06, 0.0001564723201284311, 5.344661758648963e-05, 0.0001806134468112951, 9.393092952265704e-05, 0.4996082071740686, 0.4996082071740686, 0.0001914050051051026, 8.698347206485975e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[8.71759421493796e-06, 5.110033685242944e-06, 0.33319392385959984, 3.564410667189351e-05, 0.00012045299132545165, 6.264351651959424e-05, 0.33319392385959984, 0.33319392385959984, 0.00012764999409850772, 5.801018468482596e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([0], dtype=torch.int32)
[0.2499232081887308, 3.832951086786764e-06, 0.2499232081887308, 2.6736050253469557e-05, 9.034978093019296e-05, 4.698785751986837e-05, 0.2499232081887308, 0.2499232081887308, 9.574813274150417e-05, 4.35124725448524e-05]
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.199951463382359, 0.199951463382359, 0.199951463382359, 2.139021986789052e-05, 7.228448707982863e-05, 3.759271073859039e-05, 0.199951463382359, 0.199951463382359, 7.660344710097788e-05, 3.4812223417674035e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664299781120712, 0.16664299781120712, 0.16664299781120712, 1.782697811923393e-05, 0.16664299781120712, 3.133041342812678e-05, 0.16664299781120712, 0.16664299781120712, 6.384263386544149e-05, 2.901310734446231e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([3], dtype=torch.int32)
[0.1428419358483473, 0.1428419358483473, 0.1428419358483473, 0.1428419358483473, 0.1428419358483473, 2.685559527723349e-05, 0.1428419358483473, 0.1428419358483473, 5.472420402163227e-05, 2.4869262270197752e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 84.
Rec Success! in episode: 84.
total combined:  8
-----
It has processed 85 episodes
----target item:  978
[2.2228340707331246e-05, 0.9981002160927714, 0.0002797115523832518, 9.745647348576302e-05, 0.0003271969014118657, 0.00016947951981923954, 0.0002940293327489309, 0.00020860412982431206, 0.0003429138381250192, 0.00015816381872252615]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 85.
Rec Success! in episode: 85.
total combined:  8
-----
It has processed 86 episodes
----target item:  1029
[2.3266597078492036e-05, 0.9979914479158268, 0.000297200829423169, 0.00010335474575579985, 0.0003459835264497848, 0.00017846192901334535, 0.00031244240380889736, 0.0002191408484431817, 0.00036331597897964796, 0.00016538522522109738]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 86.
Rec Success! in episode: 86.
total combined:  8
-----
It has processed 87 episodes
----target item:  1581
[0.9979722582646738, 1.4893273999597306e-05, 0.00030050825944713376, 0.0001045308704144018, 0.00034917420524285635, 0.00018085090121808657, 0.000315026707441764, 0.0002242859859902415, 0.00036975820428566345, 0.00016871332728625666]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 87.
Rec Success! in episode: 87.
total combined:  8
-----
It has processed 88 episodes
----target item:  1549
[2.265666791256023e-05, 0.9980740914760382, 0.00028327751115483365, 9.873211138164204e-05, 0.0003322676419743262, 0.00016986796158361805, 0.00029694350628553084, 0.00021241867969648982, 0.00034819332682667136, 0.00016155111714631683]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.265666791256023e-05, 0.9980740914760382, 0.00028327751115483365, 9.873211138164204e-05, 0.0003322676419743262, 0.00016986796158361805, 0.00029694350628553084, 0.00021241867969648982, 0.00034819332682667136, 0.00016155111714631683]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1339813479864388e-05, 0.49954274300630974, 0.00014178228466486898, 0.49954274300630974, 0.0001663021720548071, 8.502004831412684e-05, 0.00014862220642198357, 0.00010631696667372192, 0.00017427308359668387, 8.085741217433685e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.562895967738117e-06, 0.33316154657249614, 0.33316154657249614, 0.33316154657249614, 0.00011091240862935535, 5.670267696321045e-05, 9.912105588518055e-05, 7.090629488629429e-05, 0.00011622847267805415, 5.392647750166911e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990477518111914, 0.24990477518111914, 0.24990477518111914, 0.24990477518111914, 8.319549728493086e-05, 4.253272889515559e-05, 7.435079300579199e-05, 5.318687545061467e-05, 8.718308170037725e-05, 4.045029918670944e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 88.
Rec Success! in episode: 88.
total combined:  8
-----
It has processed 89 episodes
----target item:  841
[2.506528280551798e-05, 1.472867500432418e-05, 0.9983210326858638, 0.00010112412090800484, 0.00033704816855076417, 0.00017215110206533727, 0.0002998013540360987, 0.00021432526224768287, 0.0003523347091045441, 0.0001623886394140296]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49958617190388455, 7.370617388306718e-06, 0.49958617190388455, 5.0605176889499265e-05, 0.0001686677919831788, 8.614895134330928e-05, 0.00015002850374847823, 0.00010725401329124195, 0.00017631758000414248, 8.126355758254684e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331509964499945, 0.3331509964499945, 0.3331509964499945, 3.374626051400889e-05, 0.00011247677803825837, 5.74487657930358e-05, 0.00010004709563763372, 7.152275905689531e-05, 0.0001175780691570718, 5.4190921819400504e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991617658076104, 0.24991617658076104, 0.24991617658076104, 2.5315056810359267e-05, 8.437545323585331e-05, 4.3095701496525886e-05, 0.24991617658076104, 5.3653432444976166e-05, 8.820223204073257e-05, 4.065180092752425e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 89.
Rec Success! in episode: 89.
total combined:  8
-----
It has processed 90 episodes
----target item:  505
[2.4978399098336746e-05, 1.4875564451210216e-05, 0.0002963002136860034, 0.00010348154469440864, 0.9983133790569276, 0.00018043878020057404, 0.0003111254291559, 0.00022443291251660917, 0.0003650106413775604, 0.00016597745789158832]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2501594387170142e-05, 7.445163812024307e-06, 0.49965207486359653, 5.179212219463091e-05, 0.49965207486359653, 9.030892784211818e-05, 0.00015571710194590884, 0.00011232782486851683, 0.00018268644709928334, 8.307109065738395e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331814415742288, 4.964635466236647e-06, 0.3331814415742288, 3.4536380019449776e-05, 0.3331814415742288, 6.0220421927947004e-05, 0.00010383635156175966, 7.490321465953484e-05, 0.00012182023624585171, 5.539403743280076e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499154818117399, 0.2499154818117399, 0.2499154818117399, 2.590533257738851e-05, 0.2499154818117399, 4.517063042263168e-05, 7.788642640934416e-05, 5.6184020611830374e-05, 9.137592685821694e-05, 4.155041616095451e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2184]
random_location_list [2184]
Random Combined Rec Success! in episode: 90.
Random Combined Rec Success! in episode: 90.
Rec Success! in episode: 90.
total combined:  9
-----
It has processed 91 episodes
----target item:  1433
[0.9980227055759245, 1.549532611193771e-05, 0.00029042301484426047, 0.00010086225714988436, 0.0003426386553048944, 0.000177502037761856, 0.0003073686322674509, 0.00021912285677926484, 0.00036082148916018983, 0.0001630601546954374]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 91.
Rec Success! in episode: 91.
total combined:  9
-----
It has processed 92 episodes
----target item:  2045
[2.315426633914252e-05, 0.9980434644464904, 0.000288632095737019, 0.00010099489560928491, 0.00033595136005078115, 0.00017423950403432727, 0.000300546371215356, 0.00021449803594196485, 0.0003555403115598304, 0.00016297871302174325]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 92.
Rec Success! in episode: 92.
total combined:  9
-----
It has processed 93 episodes
----target item:  2045
[2.293852041183469e-05, 0.9980199605854988, 0.00029194300692697816, 0.00010230679088899693, 0.00033998174046147013, 0.00017655750021197772, 0.0003047080616754719, 0.00021689946666141077, 0.00035969023727005996, 0.0001650140899930818]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 93.
Rec Success! in episode: 93.
total combined:  9
-----
It has processed 94 episodes
----target item:  1023
[2.300561886426516e-05, 0.9980342261222815, 0.0002890027198392511, 9.896226290978268e-05, 0.00033785081617319934, 0.00017478102884566158, 0.0003056233437372298, 0.00021801893274812887, 0.0003552974933541253, 0.0001632316612466431]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 94.
Rec Success! in episode: 94.
total combined:  9
-----
It has processed 95 episodes
----target item:  2000
[2.3223236356768258e-05, 0.9980496223774457, 0.00028799006941117745, 9.923720501294813e-05, 0.00033471626465569817, 0.00017363295444629504, 0.0003010003101810056, 0.0002152310870279478, 0.00035292006650898696, 0.00016242642895328873]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 95.
Rec Success! in episode: 95.
total combined:  9
-----
It has processed 96 episodes
----target item:  1696
[2.261445787435574e-05, 0.9979801594187812, 0.0002968626427576332, 0.00010276008020263907, 0.0003460191512884355, 0.0001785840047407201, 0.00031416691784381647, 0.0002252953909621205, 0.000365300560573244, 0.00016823737497595912]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 96.
Rec Success! in episode: 96.
total combined:  9
-----
It has processed 97 episodes
----target item:  621
[2.496708920152187e-05, 1.4140704962775675e-05, 0.0002944734109255546, 0.00010274124376079581, 0.9983247938186608, 0.00017726419858212742, 0.000310331363908683, 0.00022094957220980305, 0.00036264003637419663, 0.00016769856141368088]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2495851012124216e-05, 7.077322510245991e-06, 0.49965447652212497, 5.1421263587145926e-05, 0.49965447652212497, 8.871947375951399e-05, 0.00015531864593794256, 0.00011058369332689313, 0.0001814987653942074, 8.393194022173739e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318250820007184, 4.7193414171286275e-06, 0.33318250820007184, 3.4289026480929886e-05, 0.33318250820007184, 5.916043622612556e-05, 0.00010357048411543874, 7.37400624630455e-05, 0.00012102806385360318, 5.59679852281653e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991603594394743, 0.24991603594394743, 0.24991603594394743, 2.571977028681601e-05, 0.24991603594394743, 4.437550394293123e-05, 7.768692591563977e-05, 5.5311499395872054e-05, 9.078163832688543e-05, 4.198088634230848e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2193]
random_location_list [2193]
Random Combined Rec Success! in episode: 97.
Random Combined Rec Success! in episode: 97.
Rec Success! in episode: 97.
total combined:  10
-----
It has processed 98 episodes
----target item:  559
[2.5679793115936515e-05, 1.4783464702189947e-05, 0.00029389004687980255, 0.00010234523420966445, 0.9983397191934257, 0.00017706703206866428, 0.0003044050209310379, 0.0002181112648515517, 0.0003591764466149137, 0.0001648225032003334]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3387980736829378e-05, 7.677879308305284e-06, 0.49964529607853636, 5.314419646466435e-05, 0.49964529607853636, 9.191097161513928e-05, 0.00015807244714832717, 0.00011329556091435108, 0.0001864576900120745, 8.546111672739689e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331786242880821, 5.1198425872681335e-06, 0.3331786242880821, 3.5438160643083974e-05, 0.3331786242880821, 6.12890210716597e-05, 0.00010540749786314789, 7.554891323835611e-05, 0.0001243356379690439, 5.698806238112099e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991392581467534, 0.24991392581467534, 0.24991392581467534, 2.658180688778669e-05, 0.24991392581467534, 4.597227657712233e-05, 7.906510106273819e-05, 5.666847787361262e-05, 9.326290805693642e-05, 4.274617084054935e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2187]
random_location_list [2187]
Random Combined Rec Success! in episode: 98.
Random Combined Rec Success! in episode: 98.
Rec Success! in episode: 98.
total combined:  11
-----
It has processed 99 episodes
----target item:  1275
[2.316283524974872e-05, 0.9980569858158642, 0.0002857221547090231, 9.934820566716496e-05, 0.0003343819253641471, 0.00017399671623150763, 0.00029968686909995153, 0.00021449030873099854, 0.00035207005595462245, 0.0001601551131287804]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 99.
Rec Success! in episode: 99.
total combined:  11
-----
It has processed 100 episodes
----target item:  1337
[2.538437151723987e-05, 1.4605941042736213e-05, 0.0002927806794794683, 0.00010172855199508292, 0.0003436369272397509, 0.00017773053778569637, 0.00030825944734866556, 0.0002211119492008518, 0.9983484690198616, 0.000166292574529009]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2704536547889986e-05, 7.310077055393859e-06, 0.499659981874232, 5.0913772117923456e-05, 0.0001719856604823569, 8.895174384920284e-05, 0.00015427970759148907, 0.00011066355682233811, 0.499659981874232, 8.32271970693341e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.333185002516909, 4.8745309419501634e-06, 0.333185002516909, 3.395049815201239e-05, 0.00011468407476968993, 5.9315110421910944e-05, 0.00010287732983810767, 7.379305687054528e-05, 0.333185002516909, 5.5497848278754525e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 100.
Rec Success! in episode: 100.
total combined:  11
-----
It has processed 101 episodes
----target item:  841
[2.5490653594997648e-05, 1.4849954266966812e-05, 0.9982819753781693, 0.00010391368951235855, 0.0003450483498261329, 0.00017567036788718776, 0.0003077301481729984, 0.00021934602034073735, 0.00036129389009012243, 0.00016468154813915022]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49957649731624193, 7.431455561628579e-06, 0.49957649731624193, 5.200217805207387e-05, 0.00017267470540634425, 8.79118217456459e-05, 0.00015399932417355008, 0.00010976870187460968, 0.0001808045628036186, 8.241261789867219e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.33314670773733857, 0.33314670773733857, 0.33314670773733857, 3.467808134747507e-05, 0.00011514955151948089, 5.862472342691916e-05, 0.00010269571951003264, 7.320016421624952e-05, 0.0001205710139798366, 5.4957533984185864e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991425994484195, 0.24991425994484195, 0.24991425994484195, 2.6014205858801968e-05, 8.638090751795888e-05, 4.397808541833433e-05, 0.24991425994484195, 5.491203857961632e-05, 9.044788686108592e-05, 4.12270963964623e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 101.
Rec Success! in episode: 101.
total combined:  11
-----
It has processed 102 episodes
----target item:  1998
[2.638260663178821e-05, 1.5393021719072755e-05, 0.0003062639023134547, 0.00010611765577516846, 0.00035734474142449867, 0.00018454159870961545, 0.9982278879797168, 0.00022880673343376328, 0.00037531447864516324, 0.00017194728163081251]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3205025819754627e-05, 7.704517301163361e-06, 0.49963315675141995, 5.311402334121654e-05, 0.00017885823803999952, 9.23667858066418e-05, 0.49963315675141995, 0.00011452237699235136, 0.0001878524533305831, 8.60630765284469e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317318576383054, 5.1376465699178225e-06, 0.33317318576383054, 3.5418322675754394e-05, 0.00011926904402291318, 6.159346286394504e-05, 0.33317318576383054, 7.636760024469628e-05, 0.00012526670715098373, 5.7389924980269065e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991086925189027, 0.24991086925189027, 0.24991086925189027, 2.656703536045077e-05, 8.94628731849285e-05, 4.620082438288942e-05, 0.24991086925189027, 5.7282801183650366e-05, 9.396167822045319e-05, 4.304778010642905e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 102.
Rec Success! in episode: 102.
total combined:  11
-----
It has processed 103 episodes
----target item:  1998
[2.638260663178821e-05, 1.5393021719072755e-05, 0.0003062639023134547, 0.00010611765577516846, 0.00035734474142449867, 0.00018454159870961545, 0.9982278879797168, 0.00022880673343376328, 0.00037531447864516324, 0.00017194728163081251]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3205025819754627e-05, 7.704517301163361e-06, 0.49963315675141995, 5.311402334121654e-05, 0.00017885823803999952, 9.23667858066418e-05, 0.49963315675141995, 0.00011452237699235136, 0.0001878524533305831, 8.60630765284469e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317318576383054, 5.1376465699178225e-06, 0.33317318576383054, 3.5418322675754394e-05, 0.00011926904402291318, 6.159346286394504e-05, 0.33317318576383054, 7.636760024469628e-05, 0.00012526670715098373, 5.7389924980269065e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991086925189027, 0.24991086925189027, 0.24991086925189027, 2.656703536045077e-05, 8.94628731849285e-05, 4.620082438288942e-05, 0.24991086925189027, 5.7282801183650366e-05, 9.396167822045319e-05, 4.304778010642905e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 103.
Rec Success! in episode: 103.
total combined:  11
-----
It has processed 104 episodes
----target item:  496
[2.4912320235414275e-05, 1.4269882544890394e-05, 0.00028754697362863276, 0.00010139906081243715, 0.00033995537182304617, 0.00017366906340428087, 0.000301761064806068, 0.00021512080825510985, 0.9983797706944258, 0.0001615947600643723]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2468053245822246e-05, 7.141753706601878e-06, 0.4996665113061038, 5.074793826263653e-05, 0.0001701399804209186, 8.69174412184432e-05, 0.0001510245929710572, 0.00010766310268427814, 0.4996665113061038, 8.087452528264915e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331878532613369, 4.762267496782724e-06, 0.3331878532613369, 3.3839763571443845e-05, 0.00011345282012634909, 5.795832819542366e-05, 0.00010070628866073268, 7.17919597314252e-05, 0.3331878532613369, 5.392878820719642e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991905126321196, 0.24991905126321196, 0.24991905126321196, 2.5382682843822683e-05, 8.509920422241035e-05, 4.347364483314727e-05, 7.553822827565248e-05, 5.3850037715305e-05, 0.24991905126321196, 4.045114926187253e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2182]
random_location_list [2182]
Random Combined Rec Success! in episode: 104.
Random Combined Rec Success! in episode: 104.
Rec Success! in episode: 104.
total combined:  12
-----
It has processed 105 episodes
----target item:  1401
[0.9981810693417199, 1.4346165682149604e-05, 0.00026943270091241725, 9.471604359465502e-05, 0.0003139433318285601, 0.00016171757463327867, 0.0002814972576439536, 0.00020208339232218606, 0.00032906424039357994, 0.0001521299512691831]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 105.
Rec Success! in episode: 105.
total combined:  12
-----
It has processed 106 episodes
----target item:  1801
[2.5235328204767425e-05, 1.4818212527994477e-05, 0.0002982058954640642, 0.00010383458806668291, 0.9983111922129557, 0.00017871506796073304, 0.0003103954123922551, 0.0002230759204654974, 0.0003672450426617063, 0.000167282319300663]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2630212304714937e-05, 7.4164745822326736e-06, 0.49965200379049, 5.196892551637459e-05, 0.49965200379049, 8.944639959028501e-05, 0.00015535204952012865, 0.00011164888416298301, 0.00018380513298793427, 8.372434035525392e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 106.
Rec Success! in episode: 106.
total combined:  12
-----
It has processed 107 episodes
----target item:  51
[2.6047873536559862e-05, 1.5253947672912979e-05, 0.0003105843500614611, 0.997973351185257, 0.00036287322135814177, 0.00018844239385056906, 0.0003281036278813594, 0.0002332110248771702, 0.000385534486865352, 0.0001765978886396225]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[1.3093686849002849e-05, 7.652053183435824e-06, 0.0001563648965099725, 0.4995493153392542, 0.00018245658379136568, 9.463187532763307e-05, 0.0001648694074869279, 0.4995493153392542, 0.00019365278269445062, 8.864803564914338e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33313587769742475, 5.102946546368642e-06, 0.00010427550482086194, 0.33313587769742475, 0.00012167534278719102, 6.310742879111918e-05, 0.00010994693232901771, 0.33313587769742475, 0.00012914178390506368, 5.9116968546086995e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.249907655582233, 3.8766492195888575e-06, 0.249907655582233, 0.249907655582233, 9.217491817041226e-05, 4.767877148952053e-05, 8.320390572667114e-05, 0.249907655582233, 9.765351699580119e-05, 4.478990946600344e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2123]
random_location_list [2123]
Random Combined Rec Success! in episode: 107.
Random Combined Rec Success! in episode: 107.
Rec Success! in episode: 107.
total combined:  13
-----
It has processed 108 episodes
----target item:  1037
[2.536710744861033e-05, 1.455583550886878e-05, 0.00029197006892293454, 0.00010120200766046181, 0.9983392837032184, 0.0001761905418916937, 0.00030760766629612797, 0.0002196320935323358, 0.00035941735926014947, 0.00016477361626057277]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.269594932788128e-05, 7.285030444245501e-06, 0.4996574790250165, 5.065045605771121e-05, 0.4996574790250165, 8.818136622161194e-05, 0.00015395414522822944, 0.0001099233696988095, 0.00017988430844833038, 8.246732454040947e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 108.
Rec Success! in episode: 108.
total combined:  13
-----
It has processed 109 episodes
----target item:  719
[2.3660743212336153e-05, 0.9979196919898506, 0.00030711366701898114, 0.00010762852088025246, 0.0003574991195765292, 0.00018368335384344093, 0.000321975835008644, 0.00022981628670218612, 0.0003758071137121027, 0.00017312337019484455]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 109.
Rec Success! in episode: 109.
total combined:  13
-----
It has processed 110 episodes
----target item:  1259
[0.9980603741754369, 1.5024295490988774e-05, 0.00028745492869045394, 9.986101888251522e-05, 0.0003373316770417817, 0.00017389818121508425, 0.0002988368466004479, 0.00021443104477483684, 0.00035201890086699944, 0.00016076893100023054]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 110.
Rec Success! in episode: 110.
total combined:  13
-----
It has processed 111 episodes
----target item:  619
[2.3308296976631117e-05, 0.9979908231132832, 0.0002976801119537475, 0.00010412557121313095, 0.00034636858156917384, 0.00017783917706055166, 0.0003091933679342966, 0.00022176842050644649, 0.0003630111616998239, 0.00016588219780315166]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3308296976631117e-05, 0.9979908231132832, 0.0002976801119537475, 0.00010412557121313095, 0.00034636858156917384, 0.00017783917706055166, 0.0003091933679342966, 0.00022176842050644649, 0.0003630111616998239, 0.00016588219780315166]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1666475884396495e-05, 0.499523233395105, 0.00014899749436240447, 0.499523233395105, 0.00017336747974512214, 8.901364490756204e-05, 0.00015476021153486147, 0.000111001500124747, 0.0001816975718124675, 8.302883141833352e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.780896593429798e-06, 0.3331544730025447, 0.3331544730025447, 0.3331544730025447, 0.00011562655646205124, 5.936719651187515e-05, 0.00010321653382411892, 7.403188441347554e-05, 0.00012118226888386772, 5.537565567708605e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990083610098876, 0.24990083610098876, 0.24990083610098876, 0.24990083610098876, 8.673205817988247e-05, 4.45316309626015e-05, 7.742323814423554e-05, 5.553168668672801e-05, 9.089942584820725e-05, 4.15375562231715e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 111.
Rec Success! in episode: 111.
total combined:  13
-----
It has processed 112 episodes
----target item:  1511
[0.9980064261546286, 1.4505640639089145e-05, 0.00029289963160106746, 0.00010154154438253945, 0.0003445461302181803, 0.00018013276654749893, 0.0003088294307191864, 0.00022199688689450458, 0.0003620086103434373, 0.00016711320402572875]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 112.
Rec Success! in episode: 112.
total combined:  13
-----
It has processed 113 episodes
----target item:  1197
[0.9980796383170437, 1.44013799316089e-05, 0.00028393188655000606, 0.00010106220724315988, 0.0003321512968717215, 0.00017094760201443173, 0.0002968437988893475, 0.00021292981686426695, 0.00034845196036342225, 0.00015964173422859177]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 113.
Rec Success! in episode: 113.
total combined:  13
-----
It has processed 114 episodes
----target item:  1671
[2.662969258996459e-05, 1.54501700336812e-05, 0.00031423776798788567, 0.00011001076129780356, 0.0003670596441334459, 0.00018736295286019003, 0.9981871641725741, 0.0002322633508406046, 0.0003847815232170813, 0.00017503996446499457]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3329022200570056e-05, 7.733309676249354e-06, 0.49962495160737413, 5.506394317869918e-05, 0.00018372522059949736, 9.378121620446219e-05, 0.49962495160737413, 0.0001162553172281035, 0.00019259559410995285, 8.761316205430551e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33316956476108994, 5.156874993351904e-06, 0.33316956476108994, 3.671880262155792e-05, 0.00012251520182457264, 6.253700277595422e-05, 0.33316956476108994, 7.752361710006722e-05, 0.00012843031569596548, 5.842390171881276e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990883554217674, 0.24990883554217674, 0.24990883554217674, 2.7542591449602447e-05, 9.189804430710554e-05, 4.6908695136194536e-05, 0.24990883554217674, 5.815008009626575e-05, 9.633494183932516e-05, 4.3823478464633904e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 114.
Rec Success! in episode: 114.
total combined:  13
-----
It has processed 115 episodes
----target item:  1671
[2.518238693384579e-05, 1.4586716526091251e-05, 0.0002959722196788035, 0.00010331578623628377, 0.00034508678903245605, 0.00017593252530120635, 0.9982956006680074, 0.0002187021377291012, 0.0003611639567725973, 0.00016445681378218248]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2603799608012316e-05, 7.300660279611503e-06, 0.49964754069714035, 5.170961233687522e-05, 0.0001727161427454593, 8.805433334231287e-05, 0.49964754069714035, 0.00010946054974942515, 0.00018076277474239665, 8.231073291535181e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317944814677286, 4.86829167551619e-06, 0.33317944814677286, 3.448146683208972e-05, 0.0001151721252258747, 5.8717179211949426e-05, 0.33317944814677286, 7.299146415985667e-05, 0.0001205378524431829, 5.488718013307793e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991434218839226, 0.24991434218839226, 0.24991434218839226, 2.5864179645427615e-05, 8.638937988031002e-05, 4.404312840883254e-05, 0.24991434218839226, 5.475011694851706e-05, 9.041415450351907e-05, 4.117028704450967e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 115.
Rec Success! in episode: 115.
total combined:  13
-----
It has processed 116 episodes
----target item:  1202
[2.2174018804163272e-05, 0.9980265676318382, 0.00029097354040867385, 0.00010096574695945582, 0.0003394940085146918, 0.00017648814124013442, 0.0003044190208031601, 0.00021825670351328843, 0.0003574812786225325, 0.00016317990929597755]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 116.
Rec Success! in episode: 116.
total combined:  13
-----
It has processed 117 episodes
----target item:  722
[0.9980763290083243, 1.4766590491218202e-05, 0.0002834854841158106, 9.945530261452121e-05, 0.00033406369263445614, 0.00017099411048259404, 0.0002975449732453055, 0.00021317465832084158, 0.0003499747004666364, 0.00016021147930443233]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 117.
Rec Success! in episode: 117.
total combined:  13
-----
It has processed 118 episodes
----target item:  1112
[2.5226680314950193e-05, 1.467118955411595e-05, 0.9983090737992126, 0.00010199312795976126, 0.00033817591482624467, 0.00017291656482719436, 0.00030400508668278436, 0.00021684700490019735, 0.0003563493586364926, 0.00016074127308568866]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49958321748862805, 7.34189468391525e-06, 0.49958321748862805, 5.104036051075214e-05, 0.00016923317241132824, 8.653253394231426e-05, 0.00015213308515759426, 0.00010851661800341568, 0.00017832769811469622, 8.043965991990754e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33318184655841043, 4.896453568478694e-06, 0.33318184655841043, 3.403981752923169e-05, 0.00011286492201717659, 5.77102441335209e-05, 0.33318184655841043, 7.23718609892549e-05, 0.00011893023958859812, 5.364678694246855e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991569688645515, 0.24991569688645515, 0.24991569688645515, 2.553285782997882e-05, 8.465862090422493e-05, 4.328776020991252e-05, 0.24991569688645515, 5.428526272042396e-05, 8.920814268446913e-05, 4.023980983038277e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.199952967248205, 0.199952967248205, 0.199952967248205, 2.0428371442992495e-05, 6.773381049623111e-05, 0.199952967248205, 0.199952967248205, 4.343264346348237e-05, 7.137379946392476e-05, 3.219513410853947e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.16664003533738975, 0.16664003533738975, 0.16664003533738975, 1.7024926341402682e-05, 5.644909765513539e-05, 0.16664003533738975, 0.16664003533738975, 0.16664003533738975, 5.9482650487843465e-05, 2.683130117733815e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 118.
Rec Success! in episode: 118.
total combined:  13
-----
It has processed 119 episodes
----target item:  247
[2.57502994534698e-05, 1.506734499898873e-05, 0.9982136184960472, 0.00010781124505305402, 0.00035723431808978043, 0.00018512715621181659, 0.00031887882059816703, 0.00022844821442124407, 0.0003757114980050533, 0.00017235260712107194]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49955944302522254, 7.540504693678939e-06, 0.49955944302522254, 5.395450886725477e-05, 0.0001787791447318674, 9.264752286725558e-05, 0.00015958400392349586, 0.00011432769563725925, 0.000188026113052193, 8.625445578178981e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.33313914789180404, 0.33313914789180404, 0.33313914789180404, 3.5980421068830686e-05, 0.00011922171178694491, 6.178347192353167e-05, 0.00010642112730827013, 7.624123942965296e-05, 0.000125388199458884, 5.7520153611761364e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499107045184039, 0.2499107045184039, 0.2499107045184039, 2.6991401145987978e-05, 8.94364477279691e-05, 4.63480533396138e-05, 0.2499107045184039, 5.719382420167871e-05, 9.406235641582721e-05, 4.3149843553633435e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 119.
Rec Success! in episode: 119.
total combined:  13
-----
It has processed 120 episodes
----target item:  1110
[2.287352481237234e-05, 0.9980921789377089, 0.00028048375634246787, 9.806944474643303e-05, 0.0003292754021760904, 0.00017000871900151274, 0.0002942427913858269, 0.00021075262222565103, 0.0003456989509771938, 0.00015641585062372987]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 120.
Rec Success! in episode: 120.
total combined:  13
-----
It has processed 121 episodes
----target item:  2101
[0.9980549424831846, 1.504780184852186e-05, 0.0002862720204832216, 9.965169383635257e-05, 0.0003365073604883538, 0.00017556943187072995, 0.0003019571333837141, 0.0002146079223988088, 0.0003525560683862796, 0.0001628880841197508]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 121.
Rec Success! in episode: 121.
total combined:  13
-----
It has processed 122 episodes
----target item:  2101
[2.5535216403570474e-05, 1.5195859671492573e-05, 0.00028491080391253163, 9.904812300224479e-05, 0.9983762571105759, 0.00017411200681546863, 0.000299911817841075, 0.00021303787448704925, 0.00035012938056732887, 0.00016186180672345604]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2779804312135477e-05, 7.60518767051421e-06, 0.49966497225264844, 4.957136878918401e-05, 0.49966497225264844, 8.713916265004746e-05, 0.00015009915257149868, 0.00010662068822871155, 0.00017523191880817627, 8.100821167292808e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331872381934734, 5.0713010048669745e-06, 0.3331872381934734, 3.30552437683925e-05, 0.3331872381934734, 5.810624829466879e-05, 0.00010008930959281057, 7.109694418853369e-05, 0.00011684837303647865, 5.40179996940983e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499187631425522, 0.2499187631425522, 0.2499187631425522, 2.479424386949413e-05, 0.2499187631425522, 4.358462762077697e-05, 7.507549386601083e-05, 5.332875427988544e-05, 8.764621665232892e-05, 4.0518093502562776e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 122.
Rec Success! in episode: 122.
total combined:  13
-----
It has processed 123 episodes
----target item:  2101
[0.9980549424831846, 1.504780184852186e-05, 0.0002862720204832216, 9.965169383635257e-05, 0.0003365073604883538, 0.00017556943187072995, 0.0003019571333837141, 0.0002146079223988088, 0.0003525560683862796, 0.0001628880841197508]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 123.
Rec Success! in episode: 123.
total combined:  13
-----
It has processed 124 episodes
----target item:  2101
[2.5535216403570474e-05, 1.5195859671492573e-05, 0.00028491080391253163, 9.904812300224479e-05, 0.9983762571105759, 0.00017411200681546863, 0.000299911817841075, 0.00021303787448704925, 0.00035012938056732887, 0.00016186180672345604]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2779804312135477e-05, 7.60518767051421e-06, 0.49966497225264844, 4.957136878918401e-05, 0.49966497225264844, 8.713916265004746e-05, 0.00015009915257149868, 0.00010662068822871155, 0.00017523191880817627, 8.100821167292808e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331872381934734, 5.0713010048669745e-06, 0.3331872381934734, 3.30552437683925e-05, 0.3331872381934734, 5.810624829466879e-05, 0.00010008930959281057, 7.109694418853369e-05, 0.00011684837303647865, 5.40179996940983e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499187631425522, 0.2499187631425522, 0.2499187631425522, 2.479424386949413e-05, 0.2499187631425522, 4.358462762077697e-05, 7.507549386601083e-05, 5.332875427988544e-05, 8.764621665232892e-05, 4.0518093502562776e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 124.
Rec Success! in episode: 124.
total combined:  13
-----
It has processed 125 episodes
----target item:  2101
[2.2723348984151807e-05, 0.9981124148564626, 0.00027645210951979227, 9.656577889249722e-05, 0.0003250956538922718, 0.00016916781267235266, 0.0002921992903525991, 0.00020764969228132793, 0.0003408903740410154, 0.00015684108290155415]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 125.
Rec Success! in episode: 125.
total combined:  13
-----
It has processed 126 episodes
----target item:  74
[2.6030861359604865e-05, 1.484564477264054e-05, 0.00028324101980624464, 9.860606528650004e-05, 0.00032725274828463547, 0.00016922819350143937, 0.00029386748085498534, 0.0002087681686261197, 0.0003447564635035007, 0.9982334033540045]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3028784126022993e-05, 7.430437982144872e-06, 0.49962878062372273, 4.935361609385637e-05, 0.00016379424995381625, 8.470090830680714e-05, 0.00014708449009141498, 0.0001044911792905868, 0.0001725550867098321, 0.49962878062372273]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331712006964598, 4.954894594185119e-06, 0.3331712006964598, 3.2910841349401466e-05, 0.00010922414608734796, 5.6481740874556376e-05, 9.808145180589403e-05, 6.967863545205243e-05, 0.00011506620045712155, 0.3331712006964598]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990971812076276, 0.24990971812076276, 0.24990971812076276, 2.4686224582296133e-05, 8.19283764731475e-05, 4.236661485573694e-05, 7.357030836533109e-05, 5.226552627736423e-05, 8.631046639491847e-05, 0.24990971812076276]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 126.
Rec Success! in episode: 126.
total combined:  13
-----
It has processed 127 episodes
----target item:  1905
[0.9978861326792864, 1.5482368667893084e-05, 0.0003116461754315852, 0.00010864388961718136, 0.0003658356697869949, 0.0001885258761292133, 0.0003303390842856925, 0.00023442809823430802, 0.000383706889609513, 0.00017525926895135325]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 127.
Rec Success! in episode: 127.
total combined:  13
-----
It has processed 128 episodes
----target item:  1562
[2.6215028180855113e-05, 1.530444781672091e-05, 0.00028623656045516875, 9.946958205238632e-05, 0.0003359749932156418, 0.00017327460111855612, 0.9983359906601832, 0.0002128817631154824, 0.00035350517993605705, 0.00016114718392593017]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([7], dtype=torch.int32)
[1.3119826333085847e-05, 7.659411849337314e-06, 0.00014325271510080617, 4.978150826116612e-05, 0.00016814529180891896, 8.67186813199918e-05, 0.499636877334975, 0.499636877334975, 0.00017691861845849243, 8.064927691811785e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[8.749504577861583e-06, 5.107998942829114e-06, 0.3332037356688558, 3.319887957095241e-05, 0.00011213471604558789, 5.783197733966707e-05, 0.3332037356688558, 0.3332037356688558, 0.0001179855756328019, 5.378434132293338e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([0], dtype=torch.int32)
[0.24992873445129957, 3.831396754292699e-06, 0.24992873445129957, 2.4901743492501856e-05, 8.410976429502602e-05, 4.3378483972591946e-05, 0.24992873445129957, 0.24992873445129957, 8.849836434823163e-05, 4.0342441939176336e-05]
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.19995500036884453, 0.19995500036884453, 0.19995500036884453, 1.9922591694626932e-05, 6.729185416618231e-05, 3.470487216198697e-05, 0.19995500036884453, 0.19995500036884453, 7.080294514651307e-05, 3.227589260809842e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664476096381187, 0.16664476096381187, 0.16664476096381187, 1.6603713458560873e-05, 0.16664476096381187, 2.8923433347731824e-05, 0.16664476096381187, 0.16664476096381187, 5.900797603315638e-05, 2.6899094289458333e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([3], dtype=torch.int32)
[0.14284308151500463, 0.14284308151500463, 0.14284308151500463, 0.14284308151500463, 0.14284308151500463, 2.4792332645135174e-05, 0.14284308151500463, 0.14284308151500463, 5.057993471735959e-05, 2.3057127605129374e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 128.
Rec Success! in episode: 128.
total combined:  13
-----
It has processed 129 episodes
----target item:  588
[2.2806858125556502e-05, 0.997992765255365, 0.0002961190977211525, 0.00010301943434708305, 0.00034551462946552126, 0.00017727790312518322, 0.00031241613975494464, 0.00022130576641987386, 0.00036475236537169653, 0.00016402255030358083]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 129.
Rec Success! in episode: 129.
total combined:  13
-----
It has processed 130 episodes
----target item:  971
[2.4088701520641867e-05, 0.9979567526469622, 0.0003004670985298788, 0.00010566266326802635, 0.00035075163591992257, 0.0001801527333093596, 0.0003162167452676482, 0.0002262011395023975, 0.0003705493528516585, 0.0001691572828683512]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 130.
Rec Success! in episode: 130.
total combined:  13
-----
It has processed 131 episodes
----target item:  642
[2.427342793501029e-05, 1.4176931639129855e-05, 0.0002769581103703231, 0.9981942054110408, 0.000326603041942644, 0.0001669424116627778, 0.0002904003006708793, 0.00020802519977413013, 0.00034177191029954423, 0.00015664325466469196]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49955421179837894, 7.094957947375279e-06, 0.00013860588428305147, 0.49955421179837894, 0.00016345108427214856, 8.35476547768357e-05, 0.0001453331350966073, 0.00010410786212145292, 0.00017104246482197284, 7.83933599227117e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33316743611904565, 4.731836691336928e-06, 9.24403518315952e-05, 0.33316743611904565, 0.00010901034841001118, 5.572039486075215e-05, 0.33316743611904565, 6.943260347655452e-05, 0.00011407326397483828, 5.2282843618079086e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24992400065781775, 3.549565258039853e-06, 0.24992400065781775, 0.24992400065781775, 8.177360520311411e-05, 4.179839471723332e-05, 0.24992400065781775, 5.208454415319261e-05, 8.557152773628208e-05, 3.9219731661075197e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.19995192529201225, 0.19995192529201225, 0.19995192529201225, 0.19995192529201225, 6.542304762805947e-05, 3.344084391986482e-05, 0.19995192529201225, 4.167028718320861e-05, 6.846157902407606e-05, 3.137778218349263e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664236568875704, 0.16664236568875704, 0.16664236568875704, 0.16664236568875704, 0.16664236568875704, 2.7870005919154702e-05, 0.16664236568875704, 3.472852399394814e-05, 5.7056712360726516e-05, 2.6150625183965803e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.1428427010854332, 0.1428427010854332, 0.1428427010854332, 0.1428427010854332, 0.1428427010854332, 0.1428427010854332, 0.1428427010854332, 2.9768637474044916e-05, 4.8907940516657405e-05, 2.2415823976762287e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 131.
Rec Success! in episode: 131.
total combined:  13
-----
It has processed 132 episodes
----target item:  599
[2.4142008218405428e-05, 0.9979685926682437, 0.0002999975140914417, 0.0001057545086452664, 0.00034747866766814887, 0.00018175966245164517, 0.00031072236659321063, 0.00022401213602061884, 0.00036821652776913394, 0.00016932394029849304]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.4142008218405428e-05, 0.9979685926682437, 0.0002999975140914417, 0.0001057545086452664, 0.00034747866766814887, 0.00018175966245164517, 0.00031072236659321063, 0.00022401213602061884, 0.00036821652776913394, 0.00016932394029849304]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.2083916752085287e-05, 0.49951807181495883, 0.0001501592143171325, 0.49951807181495883, 0.0001739251869704134, 9.097704756302464e-05, 0.00015552737688411257, 0.00011212588359017454, 0.00018430520891430643, 8.475253509118362e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.059340639833908e-06, 0.333152435514342, 0.333152435514342, 0.333152435514342, 0.00011599900565348336, 6.067693379220426e-05, 0.00010372862829534051, 7.478210160953297e-05, 0.0001229219375480902, 5.652550943562679e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24989974189482225, 0.24989974189482225, 0.24989974189482225, 0.24989974189482225, 8.701158533662769e-05, 4.5514150512606113e-05, 7.780749793436117e-05, 5.6094525803849796e-05, 9.220452018924774e-05, 4.240014093436929e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 132.
Rec Success! in episode: 132.
total combined:  13
-----
It has processed 133 episodes
----target item:  484
[0.9980233138150968, 1.487534686807273e-05, 0.00029230050086204623, 0.00010178950407050407, 0.00034092123813693085, 0.00017727533457271568, 0.00030484698611701167, 0.0002190243441701766, 0.0003608094989650047, 0.00016484343114062954]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 133.
Rec Success! in episode: 133.
total combined:  13
-----
It has processed 134 episodes
----target item:  505
[2.516217091303551e-05, 1.4339576150145548e-05, 0.0002922913210607868, 9.954425939885933e-05, 0.00033834341351071315, 0.9981910752931998, 0.00030214092175553724, 0.00021614784268607462, 0.0003561328416310298, 0.00016482235969416637]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2594317147042416e-05, 7.177328634054323e-06, 0.4996204428878212, 4.982447569288248e-05, 0.00016934962683046075, 0.4996204428878212, 0.00015122934363813627, 0.0001081875840858857, 0.00017825369557660038, 8.24978527523168e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331673966390787, 4.786137016350823e-06, 0.3331673966390787, 3.322500328360633e-05, 0.00011292927480465875, 0.3331673966390787, 0.00010084592700836952, 7.214391695069005e-05, 0.0001188668729271455, 5.5012950773062597e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499075461721879, 0.2499075461721879, 0.2499075461721879, 2.49219435212738e-05, 8.470780227036983e-05, 0.2499075461721879, 7.564413089142327e-05, 5.411486669545962e-05, 8.916157113225733e-05, 4.126499673760353e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2184]
random_location_list [2184]
Random Combined Rec Success! in episode: 134.
Random Combined Rec Success! in episode: 134.
Rec Success! in episode: 134.
total combined:  14
-----
It has processed 135 episodes
----target item:  423
[0.9980190458508972, 1.415858820119523e-05, 0.00029166702079117804, 0.00010154989197107082, 0.0003430459050356246, 0.00017766082447261887, 0.0003077656232776374, 0.00022092356496375673, 0.00035991167353178257, 0.00016427105685759604]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2179]
random_location_list [2179]
Random Combined Rec Success! in episode: 135.
Random Combined Rec Success! in episode: 135.
Rec Success! in episode: 135.
total combined:  15
-----
It has processed 136 episodes
----target item:  1896
[2.4991328905885283e-05, 1.4465319002435839e-05, 0.0002902309667267542, 0.00010125454340679503, 0.0003369803236805672, 0.0001746580264029148, 0.9983223942052862, 0.00021684690604894204, 0.00035522835339016866, 0.00016295002714939897]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 136.
Rec Success! in episode: 136.
total combined:  15
-----
It has processed 137 episodes
----target item:  1896
[0.9979739232481675, 1.483319973256111e-05, 0.00029996955811699373, 0.00010471209335007502, 0.00034890927894040436, 0.00018094409297254025, 0.00031597228573349267, 0.0002243122067776161, 0.000367407256799548, 0.00016901677940941464]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 137.
Rec Success! in episode: 137.
total combined:  15
-----
It has processed 138 episodes
----target item:  862
[2.3694668289142135e-05, 0.9979947367784401, 0.00029516022507742164, 0.00010268264614805401, 0.0003456483955392256, 0.00017797144875581392, 0.00030885765672004103, 0.00022208220231654385, 0.00036368346866496123, 0.00016548251004884308]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 138.
Rec Success! in episode: 138.
total combined:  15
-----
It has processed 139 episodes
----target item:  414
[2.2630996520667768e-05, 0.9980925313991361, 0.0002804087132210718, 9.700686221369173e-05, 0.0003280732709295772, 0.00016896560011629184, 0.0002953031532166728, 0.00020988705232361445, 0.0003462021149375667, 0.00015899083738490544]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 139.
Rec Success! in episode: 139.
total combined:  15
-----
It has processed 140 episodes
----target item:  193
[2.2227618002265067e-05, 0.9981948484359002, 0.00026804382207937466, 9.368115046254187e-05, 0.00030886421047029614, 0.00016016428895846118, 0.0002782129897589558, 0.00019817553266353988, 0.0003257408647049121, 0.00015004108699929807]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 140.
Rec Success! in episode: 140.
total combined:  15
-----
It has processed 141 episodes
----target item:  1941
[0.9979765214739642, 1.5290684184433457e-05, 0.000298671343703979, 0.00010181722694688912, 0.00035083203155374804, 0.00018045308316109662, 0.000314375700269677, 0.0002241949240069267, 0.0003693523555881916, 0.0001684911766207091]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 141.
Rec Success! in episode: 141.
total combined:  15
-----
It has processed 142 episodes
----target item:  1878
[0.9979249198641013, 1.5230645425815898e-05, 0.0003073882765311146, 0.00010677000970837502, 0.0003574642841832667, 0.00018453676325351953, 0.0003228620002484538, 0.00022910298496810292, 0.00037776215170972526, 0.00017396301987030393]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 142.
Rec Success! in episode: 142.
total combined:  15
-----
It has processed 143 episodes
----target item:  1662
[2.5596251072721313e-05, 1.5237106762373591e-05, 0.9982427903033424, 0.00010468927701930898, 0.0003518496463503278, 0.00018182312034759816, 0.00031574529323362844, 0.00022549017683285867, 0.0003690398290572201, 0.0001677389959814462]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 143.
Rec Success! in episode: 143.
total combined:  15
-----
It has processed 144 episodes
----target item:  550
[2.3678342205012366e-05, 0.9979866491153656, 0.000296693692530591, 0.00010251750724451724, 0.0003465785311290034, 0.0001804086591749081, 0.00031040373948418434, 0.00022182885393716404, 0.00036472984404656305, 0.00016651171488246474]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 144.
Rec Success! in episode: 144.
total combined:  15
-----
It has processed 145 episodes
----target item:  379
[2.59286221299391e-05, 1.552458933371433e-05, 0.00031664873171919397, 0.00010979381032901593, 0.0003679699296050765, 0.00019041186409601705, 0.9981727988766763, 0.0002340134665541857, 0.0003885611655407658, 0.00017834894401564186]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.297822274544532e-05, 7.770624192631647e-06, 0.4996219566680277, 5.495581367109424e-05, 0.000184182394502416, 9.530809517101693e-05, 0.4996219566680277, 0.00011713229029888191, 0.00019448906044240136, 8.927016292073958e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 145.
Rec Success! in episode: 145.
total combined:  15
-----
It has processed 146 episodes
----target item:  1276
[2.2621413155971297e-05, 0.9981828009935906, 0.00026791639945486175, 9.356328460152464e-05, 0.000313083811094027, 0.0001614892532784112, 0.0002785236909768033, 0.0001994475182556229, 0.00033065917694317996, 0.00014989445864893347]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 146.
Rec Success! in episode: 146.
total combined:  15
-----
It has processed 147 episodes
----target item:  1478
[2.6097307464904103e-05, 1.5027368482852955e-05, 0.0002869649654634906, 9.952957616898969e-05, 0.00033423156748084584, 0.00017292544824307952, 0.9983430068142597, 0.00021226205863011328, 0.0003508267849962761, 0.000159128108809921]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3061349090467116e-05, 7.5209944906991535e-06, 0.49965715971134383, 4.9813205477908016e-05, 0.00016727837482054917, 8.65468458447602e-05, 0.49965715971134383, 0.00010623428681895614, 0.00017558405652709166, 7.964146424175377e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 147.
Rec Success! in episode: 147.
total combined:  15
-----
It has processed 148 episodes
----target item:  825
[2.375537757505071e-05, 1.4096275683282818e-05, 0.00028800725924442894, 9.972844699834881e-05, 0.00033471394993432835, 0.00017336597763208654, 0.0003039245731167373, 0.00021601982163226333, 0.9983831627408274, 0.00016322557735607186]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1889012147334477e-05, 7.054857044526149e-06, 0.49966747579656484, 4.991176057093845e-05, 0.0001675165214309602, 8.676562632989402e-05, 0.00015210715680029016, 0.00010811287992948364, 0.49966747579656484, 8.169059261681212e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[7.928651197217563e-06, 4.7048064262279176e-06, 0.3332227338226183, 3.328560315204414e-05, 0.3332227338226183, 5.786304013761827e-05, 0.0001014385868165142, 7.209928833992499e-05, 0.3332227338226183, 5.4478556075654574e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 148.
Rec Success! in episode: 148.
total combined:  15
-----
It has processed 149 episodes
----target item:  615
[0.9980260186340372, 1.455170659293283e-05, 0.0002914712490326287, 9.938811013977036e-05, 0.0003413192224305394, 0.00017761002990550426, 0.00030614559399655324, 0.0002188054273859541, 0.0003605606722708321, 0.00016412935420827862]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 149.
Rec Success! in episode: 149.
total combined:  15
-----
It has processed 150 episodes
----target item:  1961
[2.530243834375181e-05, 1.4825982464385252e-05, 0.00028668115104927053, 9.995537086870792e-05, 0.9983761332523085, 0.00017239369760878786, 0.0002998630045958801, 0.00021405152185810966, 0.00035129775855686205, 0.00015949582234606101]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2663316107866388e-05, 7.4200794407846645e-06, 0.4996653839508445, 5.00254734659609e-05, 0.4996653839508445, 8.627926914257653e-05, 0.0001500748649068408, 0.00010712809760994719, 0.0001758168325183966, 7.982416511849842e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 150.
Rec Success! in episode: 150.
total combined:  15
-----
It has processed 151 episodes
----target item:  1894
[2.335784250078024e-05, 0.9980126854118528, 0.000292463378290373, 0.00010136643522233153, 0.00034190664192944954, 0.00017714108141289053, 0.00030688810670846726, 0.00021815946870081638, 0.0003603568519209624, 0.00016567478146101118]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 151.
Rec Success! in episode: 151.
total combined:  15
-----
It has processed 152 episodes
----target item:  1478
[2.5617003493079397e-05, 1.4733543773695406e-05, 0.0002957671220594736, 0.00010443248851553688, 0.0003498172849607013, 0.00017916484664159493, 0.9982736611012756, 0.0002214445031632717, 0.0003676060904362271, 0.00016775601568075693]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2821464927252035e-05, 7.374227621884128e-06, 0.49964199509389584, 5.226909107965499e-05, 0.00017508566336737477, 8.967308756593217e-05, 0.49964199509389584, 0.00011083431094537193, 0.00018398906791911244, 8.396289878195322e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 152.
Rec Success! in episode: 152.
total combined:  15
-----
It has processed 153 episodes
----target item:  199
[0.9980752320302032, 1.3716047719011143e-05, 0.00028481820906120693, 9.99624009595863e-05, 0.00033308437294728664, 0.0001726768141848153, 0.0002990012857939664, 0.0002132869721513488, 0.0003489211742628416, 0.00015930069271662183]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 153.
Rec Success! in episode: 153.
total combined:  15
-----
It has processed 154 episodes
----target item:  952
[0.9980922971259558, 1.4788365858949884e-05, 0.00028145242438855453, 9.730588508589443e-05, 0.0003301544928473893, 0.0001712714835595163, 0.00029507148398605614, 0.00021097192737539418, 0.0003471655556884472, 0.00015952125525396963]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 154.
Rec Success! in episode: 154.
total combined:  15
-----
It has processed 155 episodes
----target item:  956
[2.394934188320545e-05, 0.9979444933532938, 0.00030676187813272085, 0.00010690352882558634, 0.0003519028983270016, 0.00018332329010017643, 0.0003141392662026145, 0.00022640209554107012, 0.00037188272046441683, 0.0001702416272295418]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 155.
Rec Success! in episode: 155.
total combined:  15
-----
It has processed 156 episodes
----target item:  1238
[0.998074759244352, 1.4173034069576626e-05, 0.000284354909644364, 9.809783162701017e-05, 0.00033217004250213616, 0.0001729007679201278, 0.00029972187609107965, 0.0002131477803521079, 0.0003519656404362662, 0.00015870887300538394]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 156.
Rec Success! in episode: 156.
total combined:  15
-----
It has processed 157 episodes
----target item:  1448
[2.504626386756051e-05, 1.4579839880219919e-05, 0.00029200769233489915, 0.00010184184350398888, 0.998338454322236, 0.00017549942318920847, 0.0003097767608284205, 0.00021924003093243163, 0.0003592331169320126, 0.00016432070629522847]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2535376196987798e-05, 7.297047526003057e-06, 0.49965728074346344, 5.0970708751923776e-05, 0.49965728074346344, 8.783550727022528e-05, 0.00015503981969534295, 0.00010972719443145234, 0.00017979217527096532, 8.224068393023982e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 157.
Rec Success! in episode: 157.
total combined:  15
-----
It has processed 158 episodes
----target item:  730
[2.3475949158449155e-05, 0.998044901718162, 0.0002884899574811144, 0.00010200959550138272, 0.00033577788021579093, 0.0001739789318779073, 0.00030100924761377245, 0.00021657735576667873, 0.0003527043488135387, 0.0001610750154093572]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 158.
Rec Success! in episode: 158.
total combined:  15
-----
It has processed 159 episodes
----target item:  459
[0.9981012382346947, 1.5013709243968055e-05, 0.00027778390727078306, 9.828119984979477e-05, 0.00032870819743943333, 0.00017072154891636777, 0.0002946842168026422, 0.00021012064843624873, 0.0003455853630898016, 0.0001578629742562266]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 159.
Rec Success! in episode: 159.
total combined:  15
-----
It has processed 160 episodes
----target item:  102
[2.2771459798458794e-05, 0.9980416917582199, 0.00028715443342614954, 0.00010106074441830246, 0.0003373254442064749, 0.00017347251423698715, 0.00030341129234265194, 0.00021617677799921998, 0.00035497147863992553, 0.00016196409671198684]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2771459798458794e-05, 0.9980416917582199, 0.00028715443342614954, 0.00010106074441830246, 0.0003373254442064749, 0.00017347251423698715, 0.00030341129234265194, 0.00021617677799921998, 0.00035497147863992553, 0.00016196409671198684]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1397465692914018e-05, 0.4995352095381283, 0.00014372520833136102, 0.4995352095381283, 0.00016883657050175113, 8.68256601543576e-05, 0.00015186201613443033, 0.0001081998006565024, 0.00017766868200673445, 8.106552026513543e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.6013941735893584e-06, 0.3331586278558947, 0.3331586278558947, 0.3331586278558947, 0.00011260339428779553, 5.7907265088388326e-05, 0.0001012824320543011, 7.216247510226851e-05, 0.00011849385825086863, 5.4065613358722236e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990314018669116, 0.24990314018669116, 0.24990314018669116, 0.24990314018669116, 8.446409450447117e-05, 4.343638788028269e-05, 7.597221173291371e-05, 5.412925742838974e-05, 8.888254661241185e-05, 4.055475507693699e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 160.
Rec Success! in episode: 160.
total combined:  15
-----
It has processed 161 episodes
----target item:  348
[2.4009454177304997e-05, 0.9979387356422781, 0.00030383539913365806, 0.00010551637466191473, 0.00035462966111207076, 0.00018308298647204304, 0.0003176815075959642, 0.00022820396428020214, 0.0003729930677625805, 0.0001713119425261777]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.4009454177304997e-05, 0.9979387356422781, 0.00030383539913365806, 0.00010551637466191473, 0.00035462966111207076, 0.00018308298647204304, 0.0003176815075959642, 0.00022820396428020214, 0.0003729930677625805, 0.0001713119425261777]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.2017746999975602e-05, 0.4995105327200994, 0.0001520824642434571, 0.4995105327200994, 0.00017750714008152996, 9.164077596985761e-05, 0.00015901302697951072, 0.00011422573319902009, 0.00018669880156428455, 8.574887076358596e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.015259458420268e-06, 0.3331495098019164, 0.3331495098019164, 0.3331495098019164, 0.0001183887282265555, 6.111999165657799e-05, 0.00010605404394951467, 7.618307228636901e-05, 0.00012451912451784001, 5.719037415566202e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24989808746164285, 0.24989808746164285, 0.24989808746164285, 0.24989808746164285, 8.880432325541503e-05, 4.584659010824259e-05, 7.95519788287087e-05, 5.7145526261273196e-05, 9.340278209596629e-05, 4.289895287918414e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 161.
Rec Success! in episode: 161.
total combined:  15
-----
It has processed 162 episodes
----target item:  2048
[2.4710062406015345e-05, 1.4787789019673212e-05, 0.0002828760516106547, 9.91188761432211e-05, 0.0003305519086271407, 0.00017182254236076955, 0.9983496446671117, 0.00021497074025987796, 0.0003510916796895204, 0.00016042568277131695]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2366985325088722e-05, 7.401048479435927e-06, 0.4996577994032138, 4.9607389352610314e-05, 0.00016543586721888502, 8.599439471175864e-05, 0.4996577994032138, 0.00010758936770107803, 0.00017571568938749659, 8.029045139591557e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331839570888514, 4.9351988939833365e-06, 0.3331839570888514, 3.3079412159865e-05, 0.0001103166546189199, 5.734315115614315e-05, 0.3331839570888514, 7.174320367689244e-05, 0.00011717148973286904, 5.353962320710884e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991689159383798, 0.24991689159383798, 0.24991689159383798, 2.4812430751400937e-05, 8.274706757876484e-05, 4.301234133946367e-05, 0.24991689159383798, 5.38136308019511e-05, 8.78887889840653e-05, 4.015936519253757e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 162.
Rec Success! in episode: 162.
total combined:  15
-----
It has processed 163 episodes
----target item:  179
[0.997969586749651, 1.4901320504774225e-05, 0.00029988754727924355, 0.00010540754234509839, 0.00035387129384349935, 0.00018082792888205097, 0.0003147265289474126, 0.0002245350264572124, 0.00036876950080550744, 0.00016748656128437762]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2156]
random_location_list [2156]
Random Combined Rec Success! in episode: 163.
Random Combined Rec Success! in episode: 163.
Rec Success! in episode: 163.
total combined:  16
-----
It has processed 164 episodes
----target item:  275
[2.4379350393468196e-05, 1.4419199156850628e-05, 0.0002854853146802774, 0.00010117739612185661, 0.9983726352506381, 0.00017339308048517707, 0.00030102117651974544, 0.00021484659654506067, 0.00035197111999794796, 0.0001606715154613334]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.220134486839055e-05, 7.21650162121947e-06, 0.4996642089823949, 5.063712867834595e-05, 0.4996642089823949, 8.67795383653484e-05, 0.00015065467816526105, 0.00010752613896343156, 0.00017615403813053362, 8.041266641772018e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 164.
Rec Success! in episode: 164.
total combined:  16
-----
It has processed 165 episodes
----target item:  544
[2.4160250426126507e-05, 1.4555000171925083e-05, 0.00028331843352312594, 9.779525974741826e-05, 0.9983913752922547, 0.0001702031425451723, 0.0002965844670815973, 0.0002118863584229878, 0.0003497161488625466, 0.00016040564696422307]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2091563488367767e-05, 7.284390912675318e-06, 0.4996683597091577, 4.8943929439514036e-05, 0.4996683597091577, 8.518215116591457e-05, 0.00014843264660464067, 0.00010604349334144565, 0.00017502364182062446, 8.027876491144338e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 165.
Rec Success! in episode: 165.
total combined:  16
-----
It has processed 166 episodes
----target item:  551
[2.4969128620271403e-05, 1.5054264698466905e-05, 0.00028766963357002365, 0.00010011262777913829, 0.9983654150058, 0.00017541001203163234, 0.00030049345900270947, 0.000215890370329167, 0.00035440767670639236, 0.0001605778214621447]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.249657510980375e-05, 7.534373841725756e-06, 0.49966294720919907, 5.0104470664872914e-05, 0.49966294720919907, 8.778938278948426e-05, 0.00015039127466320352, 0.0001080490340424406, 0.00017737431765467584, 8.036615283567457e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318627484019975, 5.0240866720241614e-06, 0.33318627484019975, 3.341076625135378e-05, 0.33318627484019975, 5.8539896915554376e-05, 0.00010028421929898022, 7.204947926148709e-05, 0.00011827710756175053, 5.35899234396214e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991821228499833, 0.24991821228499833, 0.24991821228499833, 2.5060933187043895e-05, 0.24991821228499833, 4.3909931138370736e-05, 7.52217444119459e-05, 5.4043273726482416e-05, 8.87179500123476e-05, 4.019702753045156e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 166.
Rec Success! in episode: 166.
total combined:  16
-----
It has processed 167 episodes
----target item:  1669
[2.3969450163611855e-05, 1.4209466043376896e-05, 0.9983764499229916, 9.606322718874012e-05, 0.00032497457907677667, 0.00016682502587616577, 0.0002920950302936086, 0.0002089744459814019, 0.0003416191829699132, 0.00015481966941456544]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 167.
Rec Success! in episode: 167.
total combined:  16
-----
It has processed 168 episodes
----target item:  716
[0.9980312873422199, 1.4338837574001831e-05, 0.00029302486920094805, 0.00010079670941970072, 0.0003397149895630164, 0.0001763941904953617, 0.0003046944963112077, 0.00021954252537532062, 0.00035754355783204124, 0.00016266248200843807]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 168.
Rec Success! in episode: 168.
total combined:  16
-----
It has processed 169 episodes
----target item:  1187
[0.9980196333565677, 1.4914872699373492e-05, 0.00029323820994988606, 0.0001008531154534613, 0.0003399447268979313, 0.00017676675359315407, 0.00030855023902372246, 0.0002204171682670981, 0.00036040575340006955, 0.00016527580414763573]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 169.
Rec Success! in episode: 169.
total combined:  16
-----
It has processed 170 episodes
----target item:  1116
[2.2495611299893e-05, 0.9981351585973602, 0.000275462562708685, 9.488081868403857e-05, 0.00032010982401386935, 0.00016585360324512333, 0.0002889986578949103, 0.00020592425801921547, 0.0003377185920602261, 0.00015339747471334155]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 170.
Rec Success! in episode: 170.
total combined:  16
-----
It has processed 171 episodes
----target item:  1575
[2.5958195964031336e-05, 1.4593288944422299e-05, 0.0002925717420085252, 0.00010061019722877305, 0.998341532868649, 0.00017667479233199213, 0.00030613898107488454, 0.00021908104105410224, 0.00035788358601413867, 0.000164955306730219]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2991771707833567e-05, 7.303769441262129e-06, 0.4996581927130124, 5.035422013484693e-05, 0.4996581927130124, 8.842365516026719e-05, 0.00015321895860963383, 0.00010964748377866024, 0.00017911652465830405, 8.255819048458433e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 171.
Rec Success! in episode: 171.
total combined:  16
-----
It has processed 172 episodes
----target item:  215
[2.3181865747597906e-05, 0.9980086612849255, 0.0002933853666208979, 0.00010230426612306747, 0.000340748910799339, 0.0001770929551521059, 0.0003086505359833643, 0.00021923408146192944, 0.0003599487461471847, 0.00016679198703894993]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 172.
Rec Success! in episode: 172.
total combined:  16
-----
It has processed 173 episodes
----target item:  1102
[2.563265661603294e-05, 1.504925330386027e-05, 0.00029541076896998265, 0.9980709445761718, 0.0003471212518571228, 0.00017808790494741117, 0.0003110849289009515, 0.00022360246113086032, 0.00036483946304934593, 0.00016822673505253913]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49952367877848997, 7.53198799550857e-06, 0.00014784988468863932, 0.49952367877848997, 0.00017373042031946595, 8.913106418808848e-05, 0.0001556946316708338, 0.00011191060572897703, 0.000182598192780142, 8.419565564853025e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331561591684462, 5.023441926962629e-06, 9.86081377299582e-05, 0.3331561591684462, 0.00011586910095210767, 5.944575656576158e-05, 0.3331561591684462, 7.463851897081635e-05, 0.00012178344123043637, 5.61540972854905e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 173.
Rec Success! in episode: 173.
total combined:  16
-----
It has processed 174 episodes
----target item:  2060
[2.224893181224752e-05, 0.9980777875400737, 0.0002851505597778772, 9.837071617855286e-05, 0.00032792428867348697, 0.00017139270588563047, 0.00029777382274149644, 0.0002129062922804351, 0.00034738916827221173, 0.00015905597430415018]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.224893181224752e-05, 0.9980777875400737, 0.0002851505597778772, 9.837071617855286e-05, 0.00032792428867348697, 0.00017139270588563047, 0.00029777382274149644, 0.0002129062922804351, 0.00034738916827221173, 0.00015905597430415018]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1135716226554387e-05, 0.4995435784452057, 0.0001427194681670791, 0.4995435784452057, 0.00016412796143554603, 8.578301880511178e-05, 0.00014903748268581022, 0.00010656080362373472, 0.00017387024378081025, 7.960841486395034e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.426777275659088e-06, 0.33316212636160397, 0.33316212636160397, 0.33316212636160397, 0.00010946236321854704, 5.721153105356827e-05, 9.939802407975848e-05, 7.106892262048956e-05, 0.00011595981337467864, 5.3093483565337507e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990507588165314, 0.24990507588165314, 0.24990507588165314, 0.24990507588165314, 8.210777282837239e-05, 4.291439775999483e-05, 7.455850705904601e-05, 5.3308834033025984e-05, 8.698151340638444e-05, 3.982544830085498e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 174.
Rec Success! in episode: 174.
total combined:  16
-----
It has processed 175 episodes
----target item:  2060
[2.606562901052468e-05, 1.4754568007384562e-05, 0.00030030957780418494, 0.00010236449528526617, 0.0003461432650680116, 0.00018018128008193105, 0.00031380940201856, 0.00022361672654047342, 0.9983249448179917, 0.0001678102381919428]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3045699512804688e-05, 7.384577620891486e-06, 0.49965597381034327, 5.123284942528283e-05, 0.0001732427413370711, 9.017970895052104e-05, 0.00015705982623224072, 0.00011191890359930018, 0.49965597381034327, 8.398807263543572e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331832961328888, 4.924223948559661e-06, 0.3331832961328888, 3.416336546848737e-05, 0.00011552266082120827, 6.0134120769751896e-05, 0.00010473148193356685, 7.463036800386182e-05, 0.3331832961328888, 5.600538038827641e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991651766433406, 0.24991651766433406, 0.24991651766433406, 2.5625502324621287e-05, 8.665206641163452e-05, 4.510583282539122e-05, 7.855774151481682e-05, 5.597928197484986e-05, 0.24991651766433406, 4.2008917612490144e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 175.
Rec Success! in episode: 175.
total combined:  16
-----
It has processed 176 episodes
----target item:  2060
[2.3513112688580218e-05, 0.9979917979735067, 0.00029783037278272354, 0.00010271744329509222, 0.00034284738387766237, 0.0001791021176193319, 0.0003108664002565854, 0.0002224574116320955, 0.00036258700452530964, 0.00016628077981562412]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3513112688580218e-05, 0.9979917979735067, 0.00029783037278272354, 0.00010271744329509222, 0.00034284738387766237, 0.0001791021176193319, 0.0003108664002565854, 0.0002224574116320955, 0.00036258700452530964, 0.00016628077981562412]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1768978026718165e-05, 0.4995231255324013, 0.00014907252644059878, 0.4995231255324013, 0.00017160481391022744, 8.964567621131437e-05, 0.00015559742694728872, 0.0001113462272755695, 0.00018148505242797773, 8.322823395756062e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.849260831960907e-06, 0.33315444170249053, 0.33315444170249053, 0.33315444170249053, 0.0001144509694336729, 5.978873385970084e-05, 0.00010377492303227828, 7.426180748715867e-05, 0.00012104054492882187, 5.550865295468052e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990083130491908, 0.24990083130491908, 0.24990083130491908, 0.24990083130491908, 8.585025088955592e-05, 4.4847831587820936e-05, 7.784209450081141e-05, 5.570415729837193e-05, 9.079312478842712e-05, 4.163732125888453e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 176.
Rec Success! in episode: 176.
total combined:  16
-----
It has processed 177 episodes
----target item:  2060
[0.9980927659043246, 1.4177347904536317e-05, 0.00028393632815485256, 9.813831476902618e-05, 0.00032661646527666285, 0.0001708288560379497, 0.0002971856934974442, 0.00021198877124461616, 0.00034599373993837983, 0.00015836857885199597]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 177.
Rec Success! in episode: 177.
total combined:  16
-----
It has processed 178 episodes
----target item:  2060
[0.9980519910294807, 1.4409652735078052e-05, 0.00028991271526033655, 9.941816329884445e-05, 0.00033402601302112825, 0.00017472307409971744, 0.000303264253932534, 0.00021698499348855378, 0.0003532206175217197, 0.00016204948716152793]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 178.
Rec Success! in episode: 178.
total combined:  16
-----
It has processed 179 episodes
----target item:  2060
[2.4566416761955277e-05, 1.4041231624518724e-05, 0.0002895491027254537, 9.89241969118024e-05, 0.00033395941142095876, 0.00017429076269185465, 0.0003030598062105917, 0.00021649511677642838, 0.9983831196685015, 0.00016199428637506808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2294928087376358e-05, 7.027314351721194e-06, 0.4996678505830942, 4.9509291441136676e-05, 0.00016713902508899795, 8.722852886339192e-05, 0.00015167448145322738, 0.00010835084000351697, 0.4996678505830942, 8.107442452216994e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331884102978924, 4.685952267653797e-06, 0.3331884102978924, 3.3013775232881684e-05, 0.00011145160931037687, 5.81657091419856e-05, 0.00010113954559850932, 7.225048418281118e-05, 0.3331884102978924, 5.406203058859002e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991935035918134, 0.24991935035918134, 0.24991935035918134, 2.476311001252738e-05, 8.359808725168872e-05, 4.362917734428198e-05, 7.586317155810786e-05, 5.4193944062941775e-05, 0.24991935035918134, 4.055107304518411e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 179.
Rec Success! in episode: 179.
total combined:  16
-----
It has processed 180 episodes
----target item:  2060
[2.606562901052468e-05, 1.4754568007384562e-05, 0.00030030957780418494, 0.00010236449528526617, 0.0003461432650680116, 0.00018018128008193105, 0.00031380940201856, 0.00022361672654047342, 0.9983249448179917, 0.0001678102381919428]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3045699512804688e-05, 7.384577620891486e-06, 0.49965597381034327, 5.123284942528283e-05, 0.0001732427413370711, 9.017970895052104e-05, 0.00015705982623224072, 0.00011191890359930018, 0.49965597381034327, 8.398807263543572e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331832961328888, 4.924223948559661e-06, 0.3331832961328888, 3.416336546848737e-05, 0.00011552266082120827, 6.0134120769751896e-05, 0.00010473148193356685, 7.463036800386182e-05, 0.3331832961328888, 5.600538038827641e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991651766433406, 0.24991651766433406, 0.24991651766433406, 2.5625502324621287e-05, 8.665206641163452e-05, 4.510583282539122e-05, 7.855774151481682e-05, 5.597928197484986e-05, 0.24991651766433406, 4.2008917612490144e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 180.
Rec Success! in episode: 180.
total combined:  16
-----
It has processed 181 episodes
----target item:  2060
[2.2822980560253534e-05, 0.9980421165409809, 0.00028998199391373574, 9.989359994115379e-05, 0.00033399649275947676, 0.00017520123299060317, 0.0003029798449307289, 0.00021733123529600373, 0.000353621559289282, 0.00016205451933797181]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2822980560253534e-05, 0.9980421165409809, 0.00028998199391373574, 9.989359994115379e-05, 0.00033399649275947676, 0.00017520123299060317, 0.0003029798449307289, 0.00021733123529600373, 0.000353621559289282, 0.00016205451933797181]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.142324352435844e-05, 0.4995350241268882, 0.00014514033017775274, 0.4995350241268882, 0.00016717024592824434, 8.76908405953306e-05, 0.0001516459492430828, 0.00010877753760871257, 0.00017699288559442874, 8.111071355177728e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.618594501540081e-06, 0.33315885983036014, 0.33315885983036014, 0.33315885983036014, 0.00011149217940896122, 5.848434856268503e-05, 0.00010113843696149893, 7.254786682518448e-05, 0.00011804327047095491, 5.409581218888256e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990327393125705, 0.24990327393125705, 0.24990327393125705, 0.24990327393125705, 8.36305559042241e-05, 4.386925260517991e-05, 7.586418842301908e-05, 5.441833198004685e-05, 8.854454529969636e-05, 4.0577400759672716e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 181.
Rec Success! in episode: 181.
total combined:  16
-----
It has processed 182 episodes
----target item:  2060
[2.3915403450222426e-05, 1.3677357982376266e-05, 0.0002805978599166499, 9.607197950264342e-05, 0.00032271525693553134, 0.0001684716828769358, 0.00029323155280985846, 0.00020908601907633153, 0.9984356742177678, 0.00015655866968179572]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1968742433051975e-05, 6.84499323611396e-06, 0.49967877169857716, 4.808034203118968e-05, 0.00016150661215132633, 8.431361753163751e-05, 0.00014675114873683777, 0.00010463953551465299, 0.49967877169857716, 7.835161121085955e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331931937905207, 4.5643427077408824e-06, 0.3331931937905207, 3.206068303733448e-05, 0.00010769499720402185, 5.6221566927692504e-05, 9.78558360080798e-05, 6.97751896010417e-05, 0.3331931937905207, 5.2246012951952256e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992201885829496, 0.24992201885829496, 0.24992201885829496, 2.404812217053902e-05, 8.078001478952572e-05, 4.2170751899510764e-05, 7.339984293791213e-05, 5.233707223406304e-05, 0.24992201885829496, 3.918876278864738e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 182.
Rec Success! in episode: 182.
total combined:  16
-----
It has processed 183 episodes
----target item:  2061
[0.9980519910294807, 1.4409652735078052e-05, 0.00028991271526033655, 9.941816329884445e-05, 0.00033402601302112825, 0.00017472307409971744, 0.000303264253932534, 0.00021698499348855378, 0.0003532206175217197, 0.00016204948716152793]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 183.
Rec Success! in episode: 183.
total combined:  16
-----
It has processed 184 episodes
----target item:  2061
[2.3843943086790982e-05, 0.9980000264378536, 0.00029630556869707296, 0.00010188962067355865, 0.0003420478167001179, 0.0001782895616078049, 0.00030974710200559524, 0.00022110743754154207, 0.0003610348611832903, 0.0001657076506506767]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 184.
Rec Success! in episode: 184.
total combined:  16
-----
It has processed 185 episodes
----target item:  2061
[2.3843943086790982e-05, 0.9980000264378536, 0.00029630556869707296, 0.00010188962067355865, 0.0003420478167001179, 0.0001782895616078049, 0.00030974710200559524, 0.00022110743754154207, 0.0003610348611832903, 0.0001657076506506767]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 185.
Rec Success! in episode: 185.
total combined:  16
-----
It has processed 186 episodes
----target item:  2061
[2.5776848371786035e-05, 1.4908146686862259e-05, 0.0002962500062676354, 0.00010193083045086684, 0.0003417107473010097, 0.00017837971821522844, 0.0003098129843160792, 0.00022157100137166924, 0.00036159398766587157, 0.998148065729353]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[1.290152125543427e-05, 7.4616480876773175e-06, 0.00014827552607121183, 5.101720569863471e-05, 0.00017102899493095952, 0.4995811862001337, 0.000155063906367172, 0.00011089807964705728, 0.00018098071767434003, 0.4995811862001337]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[8.60426709564115e-06, 4.976313401259794e-06, 0.3331800860470306, 3.402433369006166e-05, 0.00011406245235345295, 0.3331800860470306, 0.00010341503461963084, 7.396001438784187e-05, 0.00012069944336021081, 0.3331800860470306]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[6.4544427809291724e-06, 3.7329536323522272e-06, 0.24993317585701616, 2.5523163393311596e-05, 8.556330992337275e-05, 0.24993317585701616, 0.24993317585701616, 5.548069064300151e-05, 9.054201156227952e-05, 0.24993317585701616]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[4.766628694790143e-06, 0.1999579068676727, 0.1999579068676727, 2.0419691428591613e-05, 6.845453909142289e-05, 0.1999579068676727, 0.1999579068676727, 4.438707560333683e-05, 7.243772681838548e-05, 0.1999579068676727]
[0, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[3.972556543054631e-06, 0.16664694108246536, 0.16664694108246536, 1.7017977271959405e-05, 0.16664694108246536, 0.16664694108246536, 0.16664694108246536, 3.6992637544397504e-05, 6.037033384851267e-05, 0.16664694108246536]
[0, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 186.
Rec Success! in episode: 186.
total combined:  16
-----
It has processed 187 episodes
----target item:  2061
[0.9980090729325214, 1.4779535547766472e-05, 0.00029630825459554615, 0.00010189054426462649, 0.00034205091723485534, 0.00017829117773558614, 0.0003097499097465095, 0.00022110944179725523, 0.0003610381338284407, 0.00016570915272817]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 187.
Rec Success! in episode: 187.
total combined:  16
-----
It has processed 188 episodes
----target item:  598
[2.476133751203819e-05, 1.4379147010332536e-05, 0.000281348841264036, 9.760640281216915e-05, 0.00032948090742124014, 0.0001694326126347387, 0.0002947105531132994, 0.00021193588631930003, 0.9984199684046785, 0.00015637590723437822]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2392202057256893e-05, 7.1962710041980595e-06, 0.4996750268621651, 4.884866438019989e-05, 0.00016489391886796646, 8.479522440327942e-05, 0.0001474925464268803, 0.00010606665836107368, 0.4996750268621651, 7.826079016907534e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331916227781552, 4.7985932554951355e-06, 0.3331916227781552, 3.2573102277280674e-05, 0.0001099540090263961, 5.6542866671141606e-05, 9.83504843142997e-05, 7.07270128025249e-05, 0.3331916227781552, 5.218559718720525e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499211788879372, 0.2499211788879372, 0.2499211788879372, 2.443251139778974e-05, 8.247456922897594e-05, 4.241181029201326e-05, 7.37709693271462e-05, 5.30510889542933e-05, 0.2499211788879372, 3.9143499050938426e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 188.
Rec Success! in episode: 188.
total combined:  16
-----
It has processed 189 episodes
----target item:  1112
[0.9980265080718418, 1.4927058100998003e-05, 0.0002929019901084693, 0.00010316189276968112, 0.0003421190040799282, 0.0001753802853223261, 0.0003035834378187656, 0.00021811231720125055, 0.00035795503227575913, 0.00016535091048102551]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 189.
Rec Success! in episode: 189.
total combined:  16
-----
It has processed 190 episodes
----target item:  127
[2.2787938199551502e-05, 0.9981380310763969, 0.0002737438730054496, 9.463771846034163e-05, 0.00032076524352389764, 0.00016536182658074034, 0.00028774388093497685, 0.0002064076536096539, 0.00033777050413613555, 0.00015275028515279005]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2145]
random_location_list [2145]
Random Combined Rec Success! in episode: 190.
Random Combined Rec Success! in episode: 190.
Rec Success! in episode: 190.
total combined:  17
-----
It has processed 191 episodes
----target item:  103
[0.9979718009853414, 1.5416282337356144e-05, 0.0002995391143923897, 0.00010469201329547708, 0.00035177384562999083, 0.00018245819856721872, 0.00031247437690848004, 0.00022445023513518764, 0.0003688756630394162, 0.00016851928535307779]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 191.
Rec Success! in episode: 191.
total combined:  17
-----
It has processed 192 episodes
----target item:  653
[2.3914632997733926e-05, 0.9979424823110038, 0.0003022463376791261, 0.00010705211358437294, 0.00035671632973837796, 0.00018191891417075566, 0.0003159704614404961, 0.00022845291880328592, 0.00037212147620370754, 0.00016912450437828105]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 192.
Rec Success! in episode: 192.
total combined:  17
-----
It has processed 193 episodes
----target item:  141
[2.6522111365615854e-05, 1.5402189300701876e-05, 0.0003012087454234681, 0.00010575326540429735, 0.00035133527735322923, 0.0001814874436331754, 0.0003152054262490969, 0.00022478225291363012, 0.00037194899371070225, 0.998106354294646]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3275624714803999e-05, 7.709555326261618e-06, 0.49960145338411055, 5.2934724710214126e-05, 0.0001758606329230585, 9.084341585439363e-05, 0.00015777586064953441, 0.00011251460304545095, 0.00018617881455523466, 0.49960145338411055]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33315910380847913, 5.141115034516225e-06, 0.33315910380847913, 3.529950788842998e-05, 0.00011727261893049865, 6.057890906430523e-05, 0.00010521279307848015, 7.503033480402883e-05, 0.0001241532957624493, 0.33315910380847913]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990294679496686, 0.24990294679496686, 0.24990294679496686, 2.647819297413513e-05, 8.796629812626164e-05, 4.5440294789293736e-05, 7.892021178552619e-05, 5.628032238110059e-05, 9.312750007629692e-05, 0.24990294679496686]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 193.
Rec Success! in episode: 193.
total combined:  17
-----
It has processed 194 episodes
----target item:  1863
[2.524595508804417e-05, 1.4991834312417754e-05, 0.9982685840136686, 0.00010160931086869316, 0.00034625183853171726, 0.00017776004135473345, 0.0003123214085030291, 0.00022265675757951472, 0.00036439739899781653, 0.00016618144109530292]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 194.
Rec Success! in episode: 194.
total combined:  17
-----
It has processed 195 episodes
----target item:  697
[2.4925754670406607e-05, 1.4778423579137489e-05, 0.0002883021834825657, 0.00010082008573241238, 0.0003391833791345663, 0.0001748619821795688, 0.0003050298841007032, 0.00021927924058139583, 0.9983693424713489, 0.00016347659519036088]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2474846699318821e-05, 7.396308398486349e-06, 0.4996640888637392, 5.0458456739015495e-05, 0.00016975456565350308, 8.751495993094263e-05, 0.0001526614176053425, 0.00010974491832914042, 0.4996640888637392, 8.181679916586795e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331867776445188, 4.932017762895102e-06, 0.3331867776445188, 3.364678587172324e-05, 0.00011319600103572738, 5.835686042875038e-05, 0.00010179792171624196, 7.318027554091203e-05, 0.3331867776445188, 5.4557204087361e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499184779161772, 0.2499184779161772, 0.2499184779161772, 2.5237956833942034e-05, 8.490664751177407e-05, 4.3772618581762656e-05, 7.635711666054428e-05, 5.489144318981367e-05, 0.2499184779161772, 4.092255251324138e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 195.
Rec Success! in episode: 195.
total combined:  17
-----
It has processed 196 episodes
----target item:  14
[2.5816937621197085e-05, 1.4876880776292157e-05, 0.0002965827145131294, 0.9980639635108143, 0.00034775671180646415, 0.00018042758500600787, 0.00031279993223905873, 0.0002222160418269607, 0.00036733779835210716, 0.00016822188704439342]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995219762057995, 7.445744117452054e-06, 0.00014843696303886602, 0.4995219762057995, 0.0001740490853004467, 9.030237251248514e-05, 0.0001565535336627769, 0.00011121711675429234, 0.00018384924180858258, 8.419353120605249e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.333148422163465, 5.152459430934415e-06, 0.00010304308395010091, 0.333148422163465, 0.00012077409159284044, 6.266880751806024e-05, 0.333148422163465, 7.709802459182875e-05, 0.000127556274001351, 5.8440768519864544e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991530306372023, 3.918854901500803e-06, 0.24991530306372023, 0.24991530306372023, 9.060898577908801e-05, 4.690980696609147e-05, 0.24991530306372023, 5.7883414103176684e-05, 9.569764774543998e-05, 4.376903562387907e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2114]
random_location_list [2114]
Random Combined Rec Success! in episode: 196.
Random Combined Rec Success! in episode: 196.
Rec Success! in episode: 196.
total combined:  18
-----
It has processed 197 episodes
----target item:  1842
[2.5610693357143635e-05, 1.44723784818594e-05, 0.0003047817882410256, 0.0001050850348864166, 0.9982576977507184, 0.00018661599647739957, 0.0003217861227727159, 0.00023096351016124503, 0.00037907346144964635, 0.0001739132634540075]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2818466918078572e-05, 7.2436033733495636e-06, 0.499640251667205, 5.259635201953385e-05, 0.499640251667205, 9.340360074876974e-05, 0.00016105791092564425, 0.00011560007661641143, 0.00018973092830219904, 8.704572668582029e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 197.
Rec Success! in episode: 197.
total combined:  18
-----
It has processed 198 episodes
----target item:  304
[0.9980492227144003, 1.4610958801459598e-05, 0.00029054554724149996, 0.00010213757341322118, 0.00033811788634097173, 0.0001748509211769076, 0.000299422054989404, 0.00021493612889055328, 0.0003537629059724918, 0.00016239330877322215]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 198.
Rec Success! in episode: 198.
total combined:  18
-----
It has processed 199 episodes
----target item:  498
[2.5250190461275556e-05, 1.4852970003113393e-05, 0.00028754829422417014, 0.00010143560977757566, 0.9983571540916977, 0.00017467921900548151, 0.00030323965275488597, 0.00021862688615188844, 0.0003554789119493164, 0.00016173417397444747]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2637292708928255e-05, 7.433659948590856e-06, 0.4996608482481929, 5.0766804861680736e-05, 0.4996608482481929, 8.742399088532416e-05, 0.00015176631078067795, 0.00010941905402971671, 0.00017791117532536463, 8.094521507417449e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 199.
Rec Success! in episode: 199.
total combined:  18
-----
It has processed 200 episodes
----target item:  416
[0.9981110013812227, 1.4160710336692651e-05, 0.0002795680136761646, 9.598067549432546e-05, 0.00032624108521403766, 0.00016953937463183816, 0.00029208043637902114, 0.00020769589040706517, 0.0003457401456811664, 0.00015799228695733095]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 200.
Rec Success! in episode: 200.
total combined:  18
-----
It has processed 201 episodes
----target item:  630
[2.2505309416352517e-05, 0.9979695525318636, 0.00029770267301789706, 0.00010254857237183346, 0.00034716582571493997, 0.00018149063139940628, 0.00031524701003435784, 0.00022412272588686425, 0.0003697698463041713, 0.0001698948739905757]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2194]
random_location_list [2194]
Random Combined Rec Success! in episode: 201.
Random Combined Rec Success! in episode: 201.
Rec Success! in episode: 201.
total combined:  19
-----
It has processed 202 episodes
----target item:  459
[2.282117365812174e-05, 0.9980543511294852, 0.00028634973683803534, 9.995867793991752e-05, 0.0003342804762024948, 0.00017338513485234592, 0.0003005865257625018, 0.00021505063573818735, 0.0003517550535450806, 0.0001614614559781904]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 202.
Rec Success! in episode: 202.
total combined:  19
-----
It has processed 203 episodes
----target item:  1393
[2.360188197446201e-05, 1.3449243949916907e-05, 0.0002745567485186203, 9.705224357487311e-05, 0.00031871588235658045, 0.00016476991565695916, 0.998413204664147, 0.00020511696399111301, 0.0003358749667185089, 0.00015365748911199607]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1811934071283026e-05, 6.730886249533572e-06, 0.4996716347514965, 4.8571325956841786e-05, 0.00015950638995399595, 8.246170295982213e-05, 0.4996716347514965, 0.00010265401963226232, 0.00016809392434748166, 7.690031383572152e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[7.877184750875911e-06, 4.488717444978684e-06, 0.3332228031376231, 3.239141920773508e-05, 0.3332228031376231, 5.499235478003419e-05, 0.3332228031376231, 6.845827898999942e-05, 0.00011209907620497289, 5.128355575206146e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 203.
Rec Success! in episode: 203.
total combined:  19
-----
It has processed 204 episodes
----target item:  135
[2.476756860361076e-05, 1.4570017570817623e-05, 0.9982854187416662, 0.00010329816020480957, 0.00034172787535353803, 0.0001776462918843383, 0.00030580607762867133, 0.00021866744258268992, 0.000361637489580811, 0.0001664603349245522]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49957717886084113, 7.291349885844176e-06, 0.49957717886084113, 5.169403708378544e-05, 0.00017101266301417157, 8.89004603979228e-05, 0.00015303613042129928, 0.00010942888879602515, 0.00018097613510455434, 8.330261361391117e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331469796916627, 0.3331469796916627, 0.3331469796916627, 3.447257611286742e-05, 0.00011404114235584249, 5.928397278334473e-05, 0.00010205334989442515, 7.297351707805997e-05, 0.0001206853622574041, 5.5551004529825615e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499142925406926, 0.2499142925406926, 0.2499142925406926, 2.5860025743820493e-05, 8.554936154237643e-05, 4.447259924392482e-05, 0.2499142925406926, 5.4741978785605385e-05, 9.053360458645381e-05, 4.167226732730789e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2149]
random_location_list [2149]
Random Combined Rec Success! in episode: 204.
Random Combined Rec Success! in episode: 204.
Rec Success! in episode: 204.
total combined:  20
-----
It has processed 205 episodes
----target item:  47
[0.9980539682546088, 1.4654002876258706e-05, 0.0002855793611202213, 0.00010000612173618842, 0.00033799706298356756, 0.00017416690559878464, 0.0003014270021040898, 0.0002163108560311804, 0.0003526996391942218, 0.00016319079374656857]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 205.
Rec Success! in episode: 205.
total combined:  20
-----
It has processed 206 episodes
----target item:  1670
[2.3791056474522463e-05, 0.9980032728696493, 0.00029509503801098937, 0.00010337830298592166, 0.00034510726578409676, 0.00017670948259891454, 0.00030702558485064425, 0.00021957307400707839, 0.0003618211643503121, 0.0001642261612882694]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3791056474522463e-05, 0.9980032728696493, 0.00029509503801098937, 0.00010337830298592166, 0.00034510726578409676, 0.00017670948259891454, 0.00030702558485064425, 0.00021957307400707839, 0.0003618211643503121, 0.0001642261612882694]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1908032298926893e-05, 0.49952616524168353, 0.00014770261453714843, 0.49952616524168353, 0.00017273501376251343, 8.844761595887772e-05, 0.0001536741583928242, 0.00010990193983402903, 0.00018110074750706648, 8.219939434147145e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.941979023803071e-06, 0.33315548921946986, 0.33315548921946986, 0.33315548921946986, 0.00011520441173995163, 5.898952010015111e-05, 0.00010249190729574905, 7.32983316576814e-05, 0.00012078387946812945, 5.482231230495682e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2499014380734423, 0.2499014380734423, 0.2499014380734423, 0.2499014380734423, 8.641534988262884e-05, 4.4248305614976143e-05, 7.687964284816227e-05, 5.498140982924625e-05, 9.060053384049387e-05, 4.112246421518494e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 206.
Rec Success! in episode: 206.
total combined:  20
-----
It has processed 207 episodes
----target item:  1360
[2.2595637788388772e-05, 0.998022795219459, 0.00029187810831166733, 0.0001015828858349805, 0.00033980064251458897, 0.0001742565629903114, 0.00030775451501746426, 0.00021751805192529372, 0.00035822213222287387, 0.00016359624393542507]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2595637788388772e-05, 0.998022795219459, 0.00029187810831166733, 0.0001015828858349805, 0.00033980064251458897, 0.0001742565629903114, 0.00030775451501746426, 0.00021751805192529372, 0.00035822213222287387, 0.00016359624393542507]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1309573995661461e-05, 0.49953060664176163, 0.00014609090013652045, 0.49953060664176163, 0.00017007709834448027, 8.721893631970363e-05, 0.00015403736299390855, 0.0001088721870424645, 0.00017929742675110855, 8.188323089294417e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.542810984724304e-06, 0.33315710639754337, 0.33315710639754337, 0.33315710639754337, 0.00011343127567270946, 5.816982595459406e-05, 0.00010273372932474138, 7.261125208340181e-05, 0.0001195806845200242, 5.461122882974626e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990227315624977, 0.24990227315624977, 0.24990227315624977, 0.24990227315624977, 8.508518381654528e-05, 4.363338333780072e-05, 7.706091809260911e-05, 5.446594595737367e-05, 8.969787620701573e-05, 4.096406758955554e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 207.
Rec Success! in episode: 207.
total combined:  20
-----
It has processed 208 episodes
----target item:  660
[0.9980160743860833, 1.520541564399217e-05, 0.00029366345394704987, 0.00010377130104503217, 0.0003429254213882703, 0.00017730245256180214, 0.00030593981395803766, 0.00022007481477951077, 0.0003597189673769854, 0.00016532397321615273]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 208.
Rec Success! in episode: 208.
total combined:  20
-----
It has processed 209 episodes
----target item:  1480
[2.7715701108030232e-05, 1.601682678206273e-05, 0.0003259377077269419, 0.00011480675468893493, 0.0003796173298821253, 0.00019744319086732043, 0.9981095793936599, 0.00024433977692139223, 0.0004013061020935017, 0.00018323721626975194]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 209.
Rec Success! in episode: 209.
total combined:  20
-----
It has processed 210 episodes
----target item:  100
[2.4625611419605303e-05, 1.415162644298407e-05, 0.00028816893494411523, 9.932197069535631e-05, 0.9983690380521987, 0.00017424690085059898, 0.00030229337414169123, 0.00021431317991787925, 0.00035377789843067843, 0.00016006245095830275]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2324632000748208e-05, 7.0826094487538e-06, 0.4996639793129469, 4.9708684083060386e-05, 0.4996639793129469, 8.720713137480801e-05, 0.0001512918615127142, 0.0001072595124803743, 0.00017705884876770598, 8.010809443814846e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 210.
Rec Success! in episode: 210.
total combined:  20
-----
It has processed 211 episodes
----target item:  131
[2.4913359482916545e-05, 1.4546390835659823e-05, 0.0002865494773793287, 0.0001000481726920831, 0.000335350689272987, 0.0001742438057695425, 0.0003016963780234054, 0.00021654693270512174, 0.9983830234192866, 0.0001630813745523747]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2762561748980493e-05, 7.4195760207664944e-06, 0.4996659217590424, 5.0248582242745185e-05, 0.00016838427169951054, 8.760769152102896e-05, 0.00015142335611538664, 0.00010851303029991227, 0.4996659217590424, 8.179741226696654e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318765655552934, 4.947528016903527e-06, 0.33318765655552934, 3.3506802512683206e-05, 0.00011228214381893488, 5.841863565834248e-05, 0.00010097225160812367, 7.23587515115796e-05, 0.33318765655552934, 5.454422028540889e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499189753207739, 0.2499189753207739, 0.2499189753207739, 2.5132941108368172e-05, 8.422112217524848e-05, 4.3818926890340366e-05, 7.57377446650037e-05, 5.4275195006363045e-05, 0.2499189753207739, 4.091278705916916e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2146]
random_location_list [2146]
Random Combined Rec Success! in episode: 211.
Random Combined Rec Success! in episode: 211.
Rec Success! in episode: 211.
total combined:  21
-----
It has processed 212 episodes
----target item:  1157
[2.7369271268295616e-05, 1.581114648395775e-05, 0.0003185925505397215, 0.00011033392270164597, 0.9981918060916881, 0.00019218528715630705, 0.00033346519002771385, 0.00023780883188301798, 0.0003925328102435884, 0.0001800948980076141]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3699203274158074e-05, 7.913988924218641e-06, 0.49962720323099685, 5.5225687973504385e-05, 0.49962720323099685, 9.619493662246289e-05, 0.0001669100860693059, 0.0001190309926932308, 0.00019647533566348788, 9.014330678592125e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 212.
Rec Success! in episode: 212.
total combined:  21
-----
It has processed 213 episodes
----target item:  576
[2.32201116604898e-05, 0.9979842398841822, 0.00029811516560897315, 0.00010219581233911558, 0.0003484123186848142, 0.00017823098232261367, 0.0003116073642360738, 0.00022204639198384417, 0.0003658232063546054, 0.00016610876262763115]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 213.
Rec Success! in episode: 213.
total combined:  21
-----
It has processed 214 episodes
----target item:  87
[2.4516311096227023e-05, 1.441995956849108e-05, 0.9983393515591257, 9.919882272014861e-05, 0.00033149191356908583, 0.00017245431913608626, 0.0002988050111624762, 0.00021121781737686488, 0.0003486160246580981, 0.00015992826158673265]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2135]
random_location_list [2135]
Random Combined Rec Success! in episode: 214.
Random Combined Rec Success! in episode: 214.
Rec Success! in episode: 214.
total combined:  22
-----
It has processed 215 episodes
----target item:  987
[2.4766286985801212e-05, 1.4466570968214311e-05, 0.0002811052084529622, 9.920539111934843e-05, 0.0003310096739159564, 0.0001704374707653265, 0.00029620887490678917, 0.9982764512773787, 0.0003480690016534805, 0.0001582802438533719]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.23955679048648e-05, 7.240542875476374e-06, 0.4996390273087958, 4.9652463562808567e-05, 0.0001656708933617994, 8.530423812080634e-05, 0.00014825303546856747, 0.4996390273087958, 0.00017420911532066855, 7.921952579358593e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317561633909726, 4.82823038896752e-06, 0.33317561633909726, 3.310988382832857e-05, 0.0001104747607539317, 5.688365111372962e-05, 9.885996442758759e-05, 0.33317561633909726, 0.00011616832592418832, 5.2826166271548097e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991217877774988, 0.24991217877774988, 0.24991217877774988, 2.4835440532941488e-05, 8.286617269093916e-05, 4.2667939937708304e-05, 7.415401335625906e-05, 0.24991217877774988, 8.713686720438086e-05, 3.962445527814894e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 215.
Rec Success! in episode: 215.
total combined:  22
-----
It has processed 216 episodes
----target item:  1084
[0.9980933301469866, 1.3931199165351906e-05, 0.0002823343246939772, 9.766601172139779e-05, 0.0003290782038611712, 0.00017069521684667132, 0.0002973490096167178, 0.00021041405897469185, 0.00034719476983719816, 0.00015800705829640651]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 216.
Rec Success! in episode: 216.
total combined:  22
-----
It has processed 217 episodes
----target item:  2018
[0.9980367836845907, 1.4554197167288167e-05, 0.0002919623410595771, 0.00010113295151072588, 0.0003384796537461828, 0.00017662862537576405, 0.00030473710180803446, 0.0002170879899739283, 0.0003570251631138562, 0.00016160829165398025]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 217.
Rec Success! in episode: 217.
total combined:  22
-----
It has processed 218 episodes
----target item:  2018
[2.5561382242353846e-05, 1.4994083768872853e-05, 0.0003042729492410266, 0.00010547642162484852, 0.0003537323590071087, 0.00018411204145450888, 0.000317735030302724, 0.9981524903222698, 0.00037270353785713155, 0.00016892187223171512]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2794456565856898e-05, 7.505116574165268e-06, 0.49961377528205864, 5.279501250777675e-05, 0.00017705667324028826, 9.215516967379928e-05, 0.0001590386234248135, 0.49961377528205864, 0.0001865524791203606, 8.455190477574445e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33316447619755074, 5.004742374890878e-06, 0.33316447619755074, 3.520604026193315e-05, 0.00011806919007403088, 6.145312709989704e-05, 0.00010605396065909926, 0.33316447619755074, 0.00012440141177933085, 5.638293509864253e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499059439857511, 0.2499059439857511, 0.2499059439857511, 2.6407973701379403e-05, 8.85634409101527e-05, 4.6095856059005054e-05, 7.955084363863746e-05, 0.2499059439857511, 9.331322654411607e-05, 4.2292716142277554e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 218.
Rec Success! in episode: 218.
total combined:  22
-----
It has processed 219 episodes
----target item:  2018
[2.6275530854424622e-05, 1.5345161668517098e-05, 0.00030552612683877047, 0.0001065658022569745, 0.00035444294494397317, 0.00018485420930678328, 0.0003183963642021472, 0.9981441333041091, 0.0003746161658510371, 0.00016984438996820806]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3151978723421059e-05, 7.680881535369942e-06, 0.49961199554271235, 5.3340546065200145e-05, 0.0001774132022830226, 9.252709835653955e-05, 0.00015937041313462592, 0.49961199554271235, 0.0001875107250932192, 8.501406938380261e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331637642206501, 5.121957494389194e-06, 0.3331637642206501, 3.556987676679551e-05, 0.00011830710796053788, 6.17012334689703e-05, 0.00010627536412062155, 0.3331637642206501, 0.0001250405906206062, 5.6691207617735805e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990556536848077, 0.24990556536848077, 0.24990556536848077, 2.6680903261754714e-05, 8.874195779108556e-05, 4.62819888893545e-05, 7.971696747223544e-05, 0.24990556536848077, 9.379273152993904e-05, 4.252397713260699e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 219.
Rec Success! in episode: 219.
total combined:  22
-----
It has processed 220 episodes
----target item:  2018
[0.9980549545986697, 1.450138632258831e-05, 0.00028949314389762953, 0.00010035210493169745, 0.0003353274620792225, 0.0001749207690968567, 0.00030165470324100785, 0.00021498940061266173, 0.00035365183432713, 0.00016015459682177337]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 220.
Rec Success! in episode: 220.
total combined:  22
-----
It has processed 221 episodes
----target item:  1237
[2.390009451181907e-05, 0.9979764452183989, 0.0002985721491051121, 0.00010541490856727941, 0.00034523669880651646, 0.00018086331204299726, 0.0003127912391903092, 0.0002243009312139183, 0.0003656184433271002, 0.00016685700483623543]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 221.
Rec Success! in episode: 221.
total combined:  22
-----
It has processed 222 episodes
----target item:  1537
[2.452860682861994e-05, 1.4401408664850376e-05, 0.0002980571332638072, 0.00010244024704163556, 0.9983222318770985, 0.00017945590829198375, 0.0003087365503732637, 0.00022166142877675797, 0.0003628008495703906, 0.00016568599009018502]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2276431455973117e-05, 7.207825033797087e-06, 0.49965473115714065, 5.127077456646357e-05, 0.49965473115714065, 8.981668518349719e-05, 0.00015452092836306479, 0.00011094031372527164, 0.00018157980977227418, 8.292491761839043e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 222.
Rec Success! in episode: 222.
total combined:  22
-----
It has processed 223 episodes
----target item:  1493
[0.997981856037325, 1.513021254878245e-05, 0.0002985628635688002, 0.00010474068279456875, 0.00034951415641386807, 0.00018089499337081979, 0.0003116729160737914, 0.0002238950024165307, 0.00036625752685890957, 0.00016747560862849354]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 223.
Rec Success! in episode: 223.
total combined:  22
-----
It has processed 224 episodes
----target item:  1030
[2.424764860213478e-05, 1.4276608342690398e-05, 0.0002807144696501858, 9.66400116553599e-05, 0.9984048370386966, 0.00017092515635704701, 0.00029607656137504626, 0.0002095670365087967, 0.00034564301035780324, 0.00015707245845433433]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2135206380952384e-05, 7.145005748859357e-06, 0.4996710793696931, 4.836536958029765e-05, 0.4996710793696931, 8.554281209381704e-05, 0.000148177261878192, 0.00010488189104055769, 0.00017298375333830605, 7.860996055259153e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 224.
Rec Success! in episode: 224.
total combined:  22
-----
It has processed 225 episodes
----target item:  1478
[2.518507331397583e-05, 1.5035152837702134e-05, 0.0002960009818093143, 0.00010369154589100122, 0.0003464902405153341, 0.00018044749820291588, 0.9982813240670336, 0.00022242031189626768, 0.00036272244168658244, 0.0001666826868132232]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2605234394357741e-05, 7.5251567986922645e-06, 0.4996439726221412, 5.189805184899161e-05, 0.00017341981270427707, 9.031472659882942e-05, 0.4996439726221412, 0.00011132229517723056, 0.00018154409719410664, 8.342538100121637e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 225.
Rec Success! in episode: 225.
total combined:  22
-----
It has processed 226 episodes
----target item:  915
[2.5896450014222447e-05, 1.471376142992978e-05, 0.9982973839264597, 0.00010059781879489996, 0.0003385969774750921, 0.00017669136546470457, 0.0003073103106530927, 0.00021708545689471537, 0.000358592134065268, 0.0001631317987483374]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49958045750188745, 7.363244445083551e-06, 0.49958045750188745, 5.0342418147567034e-05, 0.0001694449325815561, 8.842210208776115e-05, 0.0001537880676269796, 0.00010863661832500339, 0.0001794511588203277, 8.163645419089247e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331484536599194, 0.3331484536599194, 0.3331484536599194, 3.3571166580909854e-05, 0.00011299544732460124, 5.896484968046586e-05, 0.00010255456584004147, 7.244503034965294e-05, 0.00011966816389779798, 5.443979656844748e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991521588740698, 0.24991521588740698, 0.24991521588740698, 2.5183803951330095e-05, 8.47648587354655e-05, 4.423317285664177e-05, 0.24991521588740698, 5.4345488327810496e-05, 8.977047525454518e-05, 4.083865124632547e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 226.
Rec Success! in episode: 226.
total combined:  22
-----
It has processed 227 episodes
----target item:  571
[2.4016084482194242e-05, 0.9979910386599955, 0.00029928609182816335, 0.00010297744672864919, 0.0003446675921477576, 0.00017845749133757683, 0.00030994159841273315, 0.00022127760579648318, 0.00036376321083554907, 0.00016457421843517995]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.4016084482194242e-05, 0.9979910386599955, 0.00029928609182816335, 0.00010297744672864919, 0.0003446675921477576, 0.00017845749133757683, 0.00030994159841273315, 0.00022127760579648318, 0.00036376321083554907, 0.00016457421843517995]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.2020735770156153e-05, 0.49952300032962854, 0.00014980123142955992, 0.49952300032962854, 0.0001725159676555901, 8.932306809481814e-05, 0.00015513461661336196, 0.00011075575758839407, 0.00018207386985166971, 8.237409373938509e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.017173961350016e-06, 0.33315454793380833, 0.33315454793380833, 0.33315454793380833, 0.0001150587243785271, 5.957360592315621e-05, 0.00010346631292774071, 7.386803876113588e-05, 0.00012143332291198642, 5.4939019710989335e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2499009225519433, 0.2499009225519433, 0.2499009225519433, 0.2499009225519433, 8.630613493998117e-05, 4.468646510237801e-05, 7.761060809179659e-05, 5.540879194954938e-05, 9.10877537541006e-05, 4.121003838916043e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 227.
Rec Success! in episode: 227.
total combined:  22
-----
It has processed 228 episodes
----target item:  1295
[0.9980247582665149, 1.3856742573896937e-05, 0.0002913900331339448, 0.00010286051097224664, 0.00034276184188000746, 0.00017594134391769417, 0.0003065078395880462, 0.00021883774309407775, 0.00035894059569561927, 0.0001641450826295149]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 228.
Rec Success! in episode: 228.
total combined:  22
-----
It has processed 229 episodes
----target item:  1301
[2.2984861408921202e-05, 0.9980566001764815, 0.0002883797459488472, 0.00010062588491906338, 0.0003346769422401507, 0.0001728578632263228, 0.00029842648798174834, 0.00021407196853554102, 0.00035100970016401786, 0.00016036636909385677]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2984861408921202e-05, 0.9980566001764815, 0.0002883797459488472, 0.00010062588491906338, 0.0003346769422401507, 0.0001728578632263228, 0.00029842648798174834, 0.00021407196853554102, 0.00035100970016401786, 0.00016036636909385677]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.150418813260948e-05, 0.4995388351989956, 0.00014433738763993596, 0.4995388351989956, 0.00016750966815413481, 8.651735346051103e-05, 0.00014936589785846744, 0.00010714548833411954, 0.0001756844017989332, 8.026521663007098e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.672555921341567e-06, 0.3331603763573664, 0.3331603763573664, 0.3331603763573664, 0.00011171820918287099, 5.7701527907964964e-05, 9.961747763947027e-05, 7.145917134584545e-05, 0.00011717023242073862, 5.353175348264447e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 8.380000945451323e-05, 4.328200943780166e-05, 7.472323114630004e-05, 5.360164003874556e-05, 8.788958090594662e-05, 4.015425489518212e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 8.380000945451323e-05, 4.328200943780166e-05, 7.472323114630004e-05, 5.360164003874556e-05, 8.788958090594662e-05, 4.015425489518212e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 8.380000945451323e-05, 4.328200943780166e-05, 7.472323114630004e-05, 5.360164003874556e-05, 8.788958090594662e-05, 4.015425489518212e-05]
[-1, 0, 0, 1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 8.380000945451323e-05, 4.328200943780166e-05, 7.472323114630004e-05, 5.360164003874556e-05, 8.788958090594662e-05, 4.015425489518212e-05]
[-1, 0, 0, 1, -1, -1, -1, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 8.380000945451323e-05, 4.328200943780166e-05, 7.472323114630004e-05, 5.360164003874556e-05, 8.788958090594662e-05, 4.015425489518212e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 0.24990413731853034, 8.380000945451323e-05, 4.328200943780166e-05, 7.472323114630004e-05, 5.360164003874556e-05, 8.788958090594662e-05, 4.015425489518212e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  22
-----
It has processed 230 episodes
----target item:  1942
[2.2167600032203408e-05, 0.9980437235921344, 0.0002878199243605059, 9.963463767956082e-05, 0.0003382440280233928, 0.0001744731231228504, 0.0003013071347390625, 0.00021590175107121415, 0.0003557210299674187, 0.00016100717886934196]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2167600032203408e-05, 0.9980437235921344, 0.0002878199243605059, 9.963463767956082e-05, 0.0003382440280233928, 0.0001744731231228504, 0.0003013071347390625, 0.00021590175107121415, 0.0003557210299674187, 0.00016100717886934196]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1095205393762519e-05, 0.49953536193018355, 0.00014405804744572462, 0.49953536193018355, 0.0001692960428138905, 8.732632914375198e-05, 0.00015080859189445074, 0.00010806195842256918, 0.00017804353581964914, 8.058642869911275e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.399806418131818e-06, 0.33315876958644175, 0.33315876958644175, 0.33315876958644175, 0.00011290984706626691, 5.824118688538257e-05, 0.00010057987631642616, 7.207055165835503e-05, 0.00011874387650415058, 5.374609582597334e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990318214308593, 0.24990318214308593, 0.24990318214308593, 0.24990318214308593, 8.469394370790587e-05, 4.3686852225184785e-05, 7.544520344529393e-05, 5.406029149581643e-05, 8.907006300698163e-05, 4.031507377503704e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 230.
Rec Success! in episode: 230.
total combined:  22
-----
It has processed 231 episodes
----target item:  610
[2.6009127290739572e-05, 1.5588135170888246e-05, 0.9982353463717742, 0.00010390680259977895, 0.0003511616159785788, 0.00018397084429817303, 0.0003161876002983447, 0.00022677349335201434, 0.00037106778359412957, 0.00016998822564304026]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4995649493602776, 7.801052112179686e-06, 0.4995649493602776, 5.1999958494371615e-05, 0.00017573815187092872, 9.206785338710684e-05, 0.0001582354733335223, 0.0001134883563624687, 0.0001857001549726664, 8.507027891154427e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331416544703869, 0.3331416544703869, 0.3331416544703869, 3.467687680528825e-05, 0.00011719336743464596, 6.139669534500895e-05, 0.00010552146912976753, 7.568124795411022e-05, 0.0001238366641659356, 5.673026800447219e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991194628786007, 0.24991194628786007, 0.24991194628786007, 2.6013456009789604e-05, 8.79146217670721e-05, 4.6057787801128596e-05, 0.24991194628786007, 5.6773590813114774e-05, 9.289820515751827e-05, 4.2557187010938046e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2192]
random_location_list [2192]
Random Combined Rec Success! in episode: 231.
Random Combined Rec Success! in episode: 231.
Rec Success! in episode: 231.
total combined:  23
-----
It has processed 232 episodes
----target item:  868
[0.9979931580640211, 1.4723791835491319e-05, 0.0002951666108426291, 0.0001039028173589342, 0.0003478733638026537, 0.00017935396637593743, 0.0003095540199453368, 0.00022388365589511255, 0.00036419184045748105, 0.00016819186946519506]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 232.
Rec Success! in episode: 232.
total combined:  23
-----
It has processed 233 episodes
----target item:  481
[2.328585332611952e-05, 0.9979743305235313, 0.0002980056919307679, 0.00010391108162426505, 0.0003487195351084842, 0.00018159704856629606, 0.00031219704258325225, 0.00022285077536354818, 0.0003679682277981539, 0.0001671342201674263]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 233.
Rec Success! in episode: 233.
total combined:  23
-----
It has processed 234 episodes
----target item:  1655
[2.430072841501407e-05, 0.9978372124923786, 0.00031950366268534736, 0.0001108592581868107, 0.0003730325289317586, 0.00019100987017601408, 0.0003343316493409847, 0.00023811764117037543, 0.000392093094202321, 0.00017953907451268616]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 234.
Rec Success! in episode: 234.
total combined:  23
-----
It has processed 235 episodes
----target item:  2009
[2.5812016349662617e-05, 1.509982048339244e-05, 0.00031605227244319186, 0.000110449995686402, 0.000367292869857579, 0.9980326993589445, 0.00033041248627485316, 0.00023455920586528737, 0.00038942571214911826, 0.0001781962619461357]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2920759501757786e-05, 7.558539648460273e-06, 0.49958671607131555, 5.52881189869864e-05, 0.00018385633938288704, 0.49958671607131555, 0.00016539507079581657, 0.00011741365133407276, 0.00019493540924187737, 8.919996847702084e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33315247147769345, 5.04045861036708e-06, 0.33315247147769345, 3.6869221881468035e-05, 0.00012260572967978336, 0.33315247147769345, 0.00011029471928150434, 7.829801487672592e-05, 0.00012999387549403227, 5.948354709577534e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24989919623745238, 0.24989919623745238, 0.24989919623745238, 2.7655772365164818e-05, 9.196711993516066e-05, 0.24989919623745238, 8.273257459393891e-05, 5.873169992674661e-05, 9.750900198237075e-05, 4.461888138681329e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 235.
Rec Success! in episode: 235.
total combined:  23
-----
It has processed 236 episodes
----target item:  2009
[2.5541623220139125e-05, 1.486974357407574e-05, 0.0003086484236357095, 0.00010796350804729984, 0.00035872036358320926, 0.9980779831617499, 0.00032270951340365565, 0.0002290982837862916, 0.0003803612106873344, 0.0001741041683123799]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.278507121718702e-05, 7.443173401210006e-06, 0.49959620753343226, 5.4042028861881935e-05, 0.00017956045142230277, 0.49959620753343226, 0.00016153492187122762, 0.00011467704494339125, 0.0001903929568211115, 8.714928459706438e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33315666207694467, 4.963494054227952e-06, 0.33315666207694467, 3.603802766314165e-05, 0.00011974022167268066, 0.33315666207694467, 0.00010771986369787828, 7.647260114085503e-05, 0.0001269638980861092, 5.811566285120112e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990153966055217, 0.24990153966055217, 0.24990153966055217, 2.703220323797303e-05, 8.98174017255214e-05, 0.24990153966055217, 8.080090496256505e-05, 5.7362265091169784e-05, 9.523589717589447e-05, 4.359268559832819e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 236.
Rec Success! in episode: 236.
total combined:  23
-----
It has processed 237 episodes
----target item:  570
[0.9980519817334199, 1.4113814422411865e-05, 0.0002912610014830855, 0.00010164546746927696, 0.0003363099616879686, 0.0001737146772361957, 0.00030047472157779877, 0.00021468031728363933, 0.0003537830562234533, 0.00016203524919618202]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2188]
random_location_list [2188]
Random Combined Rec Success! in episode: 237.
Random Combined Rec Success! in episode: 237.
Rec Success! in episode: 237.
total combined:  24
-----
It has processed 238 episodes
----target item:  869
[0.9980910626975286, 1.5221954374469324e-05, 0.0002819632761802678, 9.850116394678087e-05, 0.000329037614386577, 0.00017009510677136003, 0.0002961435863330418, 0.00021294625998490152, 0.00034717350263185063, 0.000157854837862237]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 238.
Rec Success! in episode: 238.
total combined:  24
-----
It has processed 239 episodes
----target item:  1643
[2.5085692020548742e-05, 1.4843967298503698e-05, 0.0002869084674158858, 9.953358807972025e-05, 0.998373493718846, 0.00017284759500127168, 0.00029929602497260423, 0.0002143892861067051, 0.0003518509110580558, 0.0001617507492008434]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2554857334869737e-05, 7.429091115506288e-06, 0.4996647798389654, 4.981445189333244e-05, 0.4996647798389654, 8.650655896352025e-05, 0.00014979131894574138, 0.00010729729516687954, 0.00017609392588649028, 8.095282276292819e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 239.
Rec Success! in episode: 239.
total combined:  24
-----
It has processed 240 episodes
----target item:  1091
[0.998040693982233, 1.4319528688056448e-05, 0.0002894734794700815, 9.938517287733813e-05, 0.00033961319366883027, 0.00017390549402235164, 0.0003059432002945975, 0.00021728929081894183, 0.00035674104739617465, 0.0001626356105303157]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 240.
Rec Success! in episode: 240.
total combined:  24
-----
It has processed 241 episodes
----target item:  771
[2.5687365319503733e-05, 1.4922503256540574e-05, 0.0003115015472291401, 0.00010724059932022456, 0.0003651014942177609, 0.00018732695402039106, 0.0003254040062789508, 0.00023095341196911962, 0.998257668111553, 0.00017419400683537089]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2856885610524643e-05, 7.468921588713958e-06, 0.49964192470118485, 5.367541984608919e-05, 0.00018273840423117647, 9.375976047568849e-05, 0.0001628692563015933, 0.00011559541284651727, 0.49964192470118485, 8.718653672982369e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317700718417337, 4.980512680774797e-06, 0.33317700718417337, 3.5792464282034204e-05, 0.00012185573629708395, 6.252196792388338e-05, 0.00010860636126427972, 7.708267019316892e-05, 0.33317700718417337, 5.813873483849138e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991298986073884, 0.24991298986073884, 0.24991298986073884, 2.6847596233620824e-05, 9.140286014050193e-05, 4.689714955989656e-05, 8.146462653843355e-05, 5.7818997586995494e-05, 0.24991298986073884, 4.360932698508935e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 241.
Rec Success! in episode: 241.
total combined:  24
-----
It has processed 242 episodes
----target item:  1440
[2.3016138922183356e-05, 0.9980268812924975, 0.00029213696716457024, 0.00010130851240915834, 0.0003395392573746578, 0.00017485224198258127, 0.000302488935463935, 0.00021580557982359063, 0.0003590814903093724, 0.0001648895840522335]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 242.
Rec Success! in episode: 242.
total combined:  24
-----
It has processed 243 episodes
----target item:  1331
[2.6235484693650594e-05, 1.5611908253317557e-05, 0.0002981119613009988, 0.00010434030443395956, 0.9982966876416557, 0.00018080921171165955, 0.0003134124370274856, 0.00022646027696591144, 0.0003681649906266969, 0.00017016578333058977]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3130882580692996e-05, 7.813773464779081e-06, 0.49964834799830493, 5.2222411819502804e-05, 0.49964834799830493, 9.049516546831907e-05, 0.00015686319341882559, 0.0001133435627644517, 0.0001842668934342608, 8.516812043904746e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 243.
Rec Success! in episode: 243.
total combined:  24
-----
It has processed 244 episodes
----target item:  2014
[0.9979630003733727, 1.4792452824282301e-05, 0.0003009608073506338, 0.00010587879002581464, 0.0003509206567746414, 0.00018276609270307068, 0.0003164381670819133, 0.00022582591462360849, 0.0003695427011378457, 0.00016987404410559811]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 244.
Rec Success! in episode: 244.
total combined:  24
-----
It has processed 245 episodes
----target item:  2014
[0.9980260472908765, 1.4476586842285115e-05, 0.0002920604165311972, 0.00010251496663657905, 0.0003396421206765012, 0.0001765758180262996, 0.0003063398770921921, 0.00021896790453032285, 0.00035822767773708544, 0.00016514734105117746]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 245.
Rec Success! in episode: 245.
total combined:  24
-----
It has processed 246 episodes
----target item:  2014
[2.5053346206170288e-05, 1.4473102772664728e-05, 0.00029108459700859663, 0.00010228996131708312, 0.9983491715493923, 0.00017586613829140697, 0.0003044771615324444, 0.00021792243390277895, 0.00035582924433523547, 0.00016383246524148126]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.253884777913733e-05, 7.243584592047766e-06, 0.4996597336527704, 5.1194688475300965e-05, 0.4996597336527704, 8.801853131289773e-05, 0.00015238654147280576, 0.00010906711637957113, 0.00017808753742388833, 8.199584702333308e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331848553337536, 4.8301924726966835e-06, 0.3331848553337536, 3.413782165075042e-05, 0.3331848553337536, 5.869282563112675e-05, 0.00010161492783149008, 7.27285169187769e-05, 0.00011875295605580498, 5.467675817844311e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991737728627092, 0.24991737728627092, 0.24991737728627092, 2.5606310480936546e-05, 0.24991737728627092, 4.402468123155905e-05, 7.621995973178619e-05, 5.4552660216364755e-05, 8.907495898254283e-05, 4.101228427319774e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 246.
Rec Success! in episode: 246.
total combined:  24
-----
It has processed 247 episodes
----target item:  2014
[2.3756329515626324e-05, 0.9979336067078418, 0.0003045327415321776, 0.00010700698882817423, 0.00035389217156126765, 0.0001845802038022133, 0.0003194310639622718, 0.00022866077840746234, 0.0003731910629037364, 0.00017134195164492225]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 247.
Rec Success! in episode: 247.
total combined:  24
-----
It has processed 248 episodes
----target item:  2014
[0.9979936658237779, 1.4815749629663722e-05, 0.00029657669965503893, 0.00010405396226985907, 0.0003450763970089021, 0.00017996729078966338, 0.0003115450165613059, 0.00022216574615343206, 0.00036399985162354436, 0.00016813346253073043]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 248.
Rec Success! in episode: 248.
total combined:  24
-----
It has processed 249 episodes
----target item:  2014
[2.4063184230659225e-05, 0.9979347383972765, 0.00030360416868321346, 0.00010663419827515191, 0.0003535025370968992, 0.00018444357157790288, 0.0003195148227334376, 0.00022850985262211793, 0.00037357733440352597, 0.00017141193310054722]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 249.
Rec Success! in episode: 249.
total combined:  24
-----
It has processed 250 episodes
----target item:  1030
[0.9980766924258155, 1.4284171007008344e-05, 0.0002822989418738169, 9.848680752444185e-05, 0.00033232686924967715, 0.00017228753308251097, 0.00030085375938628027, 0.00021334731815073987, 0.000349133265266628, 0.0001602889086433186]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 250.
Rec Success! in episode: 250.
total combined:  24
-----
It has processed 251 episodes
----target item:  1409
[2.283704490022199e-05, 0.9980554563647355, 0.00028527852234082443, 9.996480549436888e-05, 0.0003327938046242741, 0.0001732033932906969, 0.00030040731820944527, 0.00021502202014404132, 0.0003524427929846896, 0.00016259393327600126]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 251.
Rec Success! in episode: 251.
total combined:  24
-----
It has processed 252 episodes
----target item:  131
[2.325941756439394e-05, 0.9979419293337718, 0.00030256341645886674, 0.0001056435687013597, 0.00035291350044933643, 0.00018462212293821344, 0.000317649350321567, 0.00022669396122088761, 0.0003743515109383554, 0.0001703738176352296]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2146]
random_location_list [2146]
Random Combined Rec Success! in episode: 252.
Random Combined Rec Success! in episode: 252.
Rec Success! in episode: 252.
total combined:  25
-----
It has processed 253 episodes
----target item:  523
[2.3837193853984076e-05, 0.9979155514547086, 0.0003066754055349431, 0.00010697691006195864, 0.00035976398232074366, 0.00018604080270990782, 0.000320232640997429, 0.00023045190261452471, 0.0003782567723804506, 0.0001722129348173827]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 253.
Rec Success! in episode: 253.
total combined:  25
-----
It has processed 254 episodes
----target item:  1123
[2.4962406427100666e-05, 1.491072378184679e-05, 0.00028772253349107176, 9.922849687011349e-05, 0.9983716085291452, 0.0001727791647391052, 0.0002995791375823296, 0.00021474462102782696, 0.00035242222677863767, 0.00016204216015658048]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2493172384832975e-05, 7.4625114022260915e-06, 0.4996645113484072, 4.966182729643879e-05, 0.4996645113484072, 8.64724278845823e-05, 0.00014993321335607886, 0.0001074752779565202, 0.0001763800955749283, 8.109877732977869e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 254.
Rec Success! in episode: 254.
total combined:  25
-----
It has processed 255 episodes
----target item:  800
[0.9981662258894386, 1.4834395517212154e-05, 0.0002713153018491606, 9.365654273617261e-05, 0.0003158102848428866, 0.00016294203858539685, 0.0002843552940136761, 0.00020222283609154068, 0.00033311474002941917, 0.00015552267689616085]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 255.
Rec Success! in episode: 255.
total combined:  25
-----
It has processed 256 episodes
----target item:  1224
[2.2975156302695233e-05, 0.9980821167145887, 0.00028386509217187946, 9.979959067277661e-05, 0.0003287097052131443, 0.0001706624865194029, 0.00029453353724780005, 0.00021155846459955968, 0.0003465754331920931, 0.00015920381949171484]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 256.
Rec Success! in episode: 256.
total combined:  25
-----
It has processed 257 episodes
----target item:  1514
[2.4435181651704128e-05, 1.4337695336561773e-05, 0.0002836578368182306, 9.93438619444891e-05, 0.9983877583288461, 0.00017085716076511634, 0.00029690714632132827, 0.0002127810074187394, 0.00035027985266520466, 0.00015964192823257915]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.222918347732084e-05, 7.1756498237660155e-06, 0.49966753888498383, 4.971906214497329e-05, 0.49966753888498383, 8.550963922402401e-05, 0.00014859443321707595, 0.00010649145225533674, 0.00017530610771428234, 7.98967021754611e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 257.
Rec Success! in episode: 257.
total combined:  25
-----
It has processed 258 episodes
----target item:  1740
[2.488845425509669e-05, 1.4243086605281019e-05, 0.0002890808252199119, 9.940987052916111e-05, 0.9983591913672566, 0.0001737825794810372, 0.00030356058839965113, 0.0002164136096477097, 0.00035584326157654244, 0.00016358635702887645]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2456246717160965e-05, 7.128421835716843e-06, 0.49966174164750493, 4.975294410574673e-05, 0.49966174164750493, 8.697521601676603e-05, 0.000151926895256594, 0.00010831131926046431, 0.00017809348115417698, 8.18721806436005e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 258.
Rec Success! in episode: 258.
total combined:  25
-----
It has processed 259 episodes
----target item:  302
[2.4489795970889747e-05, 1.4608645269906756e-05, 0.00028204177746915727, 0.9981658011541241, 0.0003305672195503456, 0.00016906646488267706, 0.00029695566941761905, 0.0002121863323565781, 0.00034602297445679984, 0.00015825996650210416]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995471518857005, 7.311117180184388e-06, 0.0001411520676069958, 0.4995471518857005, 0.00016543735804433989, 8.461186599848696e-05, 0.00014861595009803177, 0.00010619185497563899, 0.00017317242403721946, 7.920359065822703e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 259.
Rec Success! in episode: 259.
total combined:  25
-----
It has processed 260 episodes
----target item:  545
[0.9979752412895526, 1.5037942717988872e-05, 0.0002985415778632409, 0.0001054801117811204, 0.00035097657281552713, 0.00018035600499483187, 0.0003122863290989776, 0.00022334186077080804, 0.00036810425502126144, 0.0001706340553836835]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 260.
Rec Success! in episode: 260.
total combined:  25
-----
It has processed 261 episodes
----target item:  1555
[2.2400779885379514e-05, 0.998044844948801, 0.00028827912881256593, 0.00010028293205422608, 0.00033476728392879435, 0.0001732490606796157, 0.00030218670071839045, 0.00021630278713086207, 0.00035398693316160927, 0.00016369944482760374]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 261.
Rec Success! in episode: 261.
total combined:  25
-----
It has processed 262 episodes
----target item:  718
[2.4318450832581794e-05, 1.42262238295772e-05, 0.00027199108078706174, 9.509043867019086e-05, 0.00031640000031521735, 0.00016521664051078277, 0.9984154947898451, 0.0002048773397256173, 0.000336629496742146, 0.0001557555387417295]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 262.
Rec Success! in episode: 262.
total combined:  25
-----
It has processed 263 episodes
----target item:  1076
[2.341203389661277e-05, 0.9980318963970696, 0.00028780332439334215, 0.00010329141148600884, 0.0003366930770086619, 0.00017712249112725913, 0.0003023508675914539, 0.00021589341378407543, 0.00035709452765878805, 0.00016444245598418793]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.341203389661277e-05, 0.9980318963970696, 0.00028780332439334215, 0.00010329141148600884, 0.0003366930770086619, 0.00017712249112725913, 0.0003023508675914539, 0.00021589341378407543, 0.00035709452765878805, 0.00016444245598418793]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1718153410582813e-05, 0.4995333136062043, 0.00014405085530842527, 0.4995333136062043, 0.00016852107536199546, 8.865306332031681e-05, 0.00015133216814503523, 0.00010805862293844744, 0.00017873237650619896, 8.230647260059351e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.815284330557216e-06, 0.3331578570128758, 0.3331578570128758, 0.3331578570128758, 0.00011239314536160783, 5.912611589445893e-05, 0.0001009292062472086, 7.206842520680367e-05, 0.00011920345232983905, 5.489333200211643e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990274656625114, 0.24990274656625114, 0.24990274656625114, 0.24990274656625114, 8.430644851938819e-05, 4.435068375184294e-05, 7.570731207144926e-05, 5.405875029142306e-05, 8.941488099515143e-05, 4.117565936609988e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 263.
Rec Success! in episode: 263.
total combined:  25
-----
It has processed 264 episodes
----target item:  969
[2.5509191533617125e-05, 1.4631325989648904e-05, 0.00030139507138311663, 0.00010545125947647551, 0.9982914843941859, 0.00018120026701879484, 0.0003151562826919903, 0.00022438070089914283, 0.00036948192597176087, 0.0001713095808492508]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.2767426460189899e-05, 7.323022305184726e-06, 0.49964786598743655, 5.2778669944362486e-05, 0.49964786598743655, 9.069127418955855e-05, 0.00015773665964419735, 0.00011230321016016366, 0.00018492680616698798, 8.574095625635179e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 264.
Rec Success! in episode: 264.
total combined:  25
-----
It has processed 265 episodes
----target item:  1244
[0.9980577703152902, 1.4462487513534518e-05, 0.00028810060189797364, 9.977916680617159e-05, 0.0003367818131999093, 0.00017402349041784353, 0.00030104228171855924, 0.0002144575034903916, 0.00035169776234116214, 0.00016188457732421328]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 265.
Rec Success! in episode: 265.
total combined:  25
-----
It has processed 266 episodes
----target item:  1149
[2.5004519411627834e-05, 1.4618936188900023e-05, 0.00029361772721047975, 0.00010137811211199971, 0.0003400749836221917, 0.00017866989032249212, 0.9983012626520764, 0.0002194952152719116, 0.0003619225890994044, 0.00016395537468484738]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 266.
Rec Success! in episode: 266.
total combined:  25
-----
It has processed 267 episodes
----target item:  459
[2.4624671098702356e-05, 1.4485076077783487e-05, 0.0002965573544990425, 0.00010119045804128583, 0.9983193360216638, 0.00017870598505242304, 0.00031146965056542904, 0.00022333233774923266, 0.00036360263828752286, 0.00016669580696486306]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2324519700986045e-05, 7.249705174755889e-06, 0.4996536309198735, 5.064529750195724e-05, 0.4996536309198735, 8.944141526336036e-05, 0.0001558889387503396, 0.00011177667248529193, 0.00018198122772657968, 8.343038364961084e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 267.
Rec Success! in episode: 267.
total combined:  25
-----
It has processed 268 episodes
----target item:  1472
[0.9979776661289812, 1.4285372772806942e-05, 0.0003019349502428818, 0.00010419102461885228, 0.00035168808049837816, 0.0001809399856785888, 0.0003124647380067442, 0.00022250422822018293, 0.0003671513643023882, 0.00016717412667804294]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 268.
Rec Success! in episode: 268.
total combined:  25
-----
It has processed 269 episodes
----target item:  1952
[2.4369678978622475e-05, 1.458059821541861e-05, 0.00027894885835286237, 9.668299062939023e-05, 0.9984086591797454, 0.00017066532783346645, 0.0002935648172875615, 0.00020921447983137563, 0.0003454821404729067, 0.00015783192865295975]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.2196244744643075e-05, 7.297122974600768e-06, 0.4996715949031931, 4.838674392857062e-05, 0.4996715949031931, 8.541253700992989e-05, 0.00014691979993648288, 0.00010470515440047391, 0.0001729027593595698, 7.89898312595397e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 269.
Rec Success! in episode: 269.
total combined:  25
-----
It has processed 270 episodes
----target item:  1125
[2.561204658446924e-05, 1.5585064705403806e-05, 0.00031211603215860833, 0.00010985916063607189, 0.9982261813103833, 0.00018858971190554772, 0.00032891188962397766, 0.00023547612323321503, 0.00038430449731353635, 0.00017336416345587727]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2819393501242792e-05, 7.800668195022427e-06, 0.4996341928106766, 5.498692989118787e-05, 0.4996341928106766, 9.439330508906808e-05, 0.0001646276460735433, 0.00011786098677893997, 0.00019235286641821556, 8.677258269951416e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 270.
Rec Success! in episode: 270.
total combined:  25
-----
It has processed 271 episodes
----target item:  1756
[0.9980147128675071, 1.520603055412119e-05, 0.00029331704014022434, 0.00010251750073940345, 0.00034377815724210176, 0.0001767337118906096, 0.0003063066480841872, 0.00022072758587886405, 0.00036073405415907906, 0.00016596640380447418]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 271.
Rec Success! in episode: 271.
total combined:  25
-----
It has processed 272 episodes
----target item:  179
[2.3086576681359037e-05, 0.9980172113325081, 0.0002940573917094551, 0.00010162559643394339, 0.0003405384673915369, 0.00017482910550572353, 0.0003057027877112545, 0.00021807525982981421, 0.00036073196591414987, 0.00016414151631481943]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2156]
random_location_list [2156]
Random Combined Rec Success! in episode: 272.
Random Combined Rec Success! in episode: 272.
Rec Success! in episode: 272.
total combined:  26
-----
It has processed 273 episodes
----target item:  553
[2.3120146147799767e-05, 0.9979601248233212, 0.00030009248001601165, 0.00010469356202030988, 0.00035114058270033774, 0.00018201099458539733, 0.00031670727438716826, 0.0002249424129675616, 0.000369819568372989, 0.00016734815548147267]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 273.
Rec Success! in episode: 273.
total combined:  26
-----
It has processed 274 episodes
----target item:  1223
[0.998085986641188, 1.492091081320391e-05, 0.0002817692423410123, 9.853227797671422e-05, 0.00033023241513525545, 0.00017180358568767102, 0.00029847435495660503, 0.0002110436003116913, 0.0003491362172868605, 0.0001581007543029571]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.998085986641188, 1.492091081320391e-05, 0.0002817692423410123, 9.853227797671422e-05, 0.00033023241513525545, 0.00017180358568767102, 0.00029847435495660503, 0.0002110436003116913, 0.0003491362172868605, 0.0001581007543029571]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.49954567255243015, 7.467970222044979e-06, 0.000141026532336669, 0.49954567255243015, 0.00016528252688178445, 8.598832055350791e-05, 0.0001493875020610344, 0.00010562809083250933, 0.0001747439487292154, 7.913000352314336e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331626815205531, 4.980623637433294e-06, 0.3331626815205531, 0.3331626815205531, 0.00011023210266854775, 5.7348308731568096e-05, 9.963121193305442e-05, 7.044668769893474e-05, 0.00011654222173650224, 5.2774281934619896e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 274.
Rec Success! in episode: 274.
total combined:  26
-----
It has processed 275 episodes
----target item:  1107
[2.2754473616230916e-05, 0.9979484067563288, 0.0003031188449997865, 0.00010459432617068574, 0.00035188614128001843, 0.0001839402326524157, 0.0003166900412119995, 0.00022604853648117206, 0.0003724570313074737, 0.00017010361595161773]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2754473616230916e-05, 0.9979484067563288, 0.0003031188449997865, 0.00010459432617068574, 0.00035188614128001843, 0.0001839402326524157, 0.0003166900412119995, 0.00022604853648117206, 0.0003724570313074737, 0.00017010361595161773]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1389515774284971e-05, 0.4995127249424136, 0.00015172299411688023, 0.4995127249424136, 0.0001761329584878747, 9.206937574798328e-05, 0.00015851591562945086, 0.00011314625051004799, 0.00018642950414347976, 8.514360076261681e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.59624650733561e-06, 0.33315040493472736, 0.33315040493472736, 0.33315040493472736, 0.00011747201525116656, 6.14057425985781e-05, 0.00010572231465502464, 7.546298080517214e-05, 0.00012433930447786081, 5.6786591522641756e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2498985125701119, 0.2498985125701119, 0.2498985125701119, 0.2498985125701119, 8.811660272672226e-05, 4.606088874979558e-05, 7.930306788291708e-05, 5.6605324135848497e-05, 9.326780572008463e-05, 4.2596030337153745e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 275.
Rec Success! in episode: 275.
total combined:  26
-----
It has processed 276 episodes
----target item:  840
[2.290787986527649e-05, 0.9979775237096169, 0.00029866343144567157, 0.00010646117437823034, 0.00034667137960675906, 0.00018003678053919646, 0.00031068612574946234, 0.0002225510631363605, 0.00036544640934512096, 0.0001690520463170173]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.290787986527649e-05, 0.9979775237096169, 0.00029866343144567157, 0.00010646117437823034, 0.00034667137960675906, 0.00018003678053919646, 0.00031068612574946234, 0.0002225510631363605, 0.00036544640934512096, 0.0001690520463170173]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1466145285775889e-05, 0.4995204857931189, 0.00014949084405210645, 0.4995204857931189, 0.00017352039684024627, 9.01143141393395e-05, 0.0001555085969137623, 0.00011139410711217263, 0.00018291791507374876, 8.461609434519529e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.647303652266122e-06, 0.33315336062645884, 0.33315336062645884, 0.33315336062645884, 0.0001157287938907613, 6.010141215410176e-05, 0.00010371588982154803, 7.429389223042603e-05, 0.00012199643429807872, 5.6434394576286746e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990018517637422, 0.24990018517637422, 0.24990018517637422, 0.24990018517637422, 8.680881072055689e-05, 4.508240288625439e-05, 7.779786469330557e-05, 5.572826097550267e-05, 9.151020258243791e-05, 4.233175264512273e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 276.
Rec Success! in episode: 276.
total combined:  26
-----
It has processed 277 episodes
----target item:  1811
[2.400401979572534e-05, 0.9979683145999949, 0.0003013531659063047, 0.00010381614492045706, 0.00035096361328816616, 0.00018023197914939447, 0.0003118072055256064, 0.00022352065113030408, 0.0003680233585734891, 0.00016796526171562143]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.400401979572534e-05, 0.9979683145999949, 0.0003013531659063047, 0.00010381614492045706, 0.00035096361328816616, 0.00018023197914939447, 0.0003118072055256064, 0.00022352065113030408, 0.0003680233585734891, 0.00016796526171562143]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.20148387512203e-05, 0.499517517515183, 0.00015083763995973583, 0.499517517515183, 0.0001756693777578821, 9.02123138424882e-05, 0.00015607024688947787, 0.00011187978529232088, 0.0001842083679138787, 8.407239922702816e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.013275813372197e-06, 0.3331523397310341, 0.3331523397310341, 0.3331523397310341, 0.0001171623860365506, 6.016694585342902e-05, 0.00010409077978341228, 7.461802826085977e-05, 0.00012285745067324588, 5.607194047691165e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24989967936695442, 0.24989967936695442, 0.24989967936695442, 0.24989967936695442, 8.788424757286472e-05, 4.513160702818322e-05, 7.807915296026923e-05, 5.597145543818667e-05, 9.215615161482111e-05, 4.205991756796864e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989967936695442, 0.24989967936695442, 0.24989967936695442, 0.24989967936695442, 8.788424757286472e-05, 4.513160702818322e-05, 7.807915296026923e-05, 5.597145543818667e-05, 9.215615161482111e-05, 4.205991756796864e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989967936695442, 0.24989967936695442, 0.24989967936695442, 0.24989967936695442, 8.788424757286472e-05, 4.513160702818322e-05, 7.807915296026923e-05, 5.597145543818667e-05, 9.215615161482111e-05, 4.205991756796864e-05]
[-1, 0, 0, 1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 277.
Rec Success! in episode: 277.
total combined:  26
-----
It has processed 278 episodes
----target item:  881
[2.3959345435335242e-05, 0.997987929443339, 0.00029613626288568426, 0.00010292648571640073, 0.00034735558101779083, 0.00017755267249851053, 0.0003112115798407236, 0.00022082163739069868, 0.0003653964863959134, 0.00016671050547988588]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 278.
Rec Success! in episode: 278.
total combined:  26
-----
It has processed 279 episodes
----target item:  674
[2.2759318115750356e-05, 0.9980427064698792, 0.0002890803955125423, 0.00010083078164969523, 0.00033631268305470813, 0.0001741268544390526, 0.00030078618886253964, 0.00021548453049350188, 0.00035536466417370274, 0.00016254811381919665]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 279.
Rec Success! in episode: 279.
total combined:  26
-----
It has processed 280 episodes
----target item:  265
[0.9980786467568011, 1.4400254008853013e-05, 0.0002844169079006154, 9.857294490229003e-05, 0.0003327694194119104, 0.00017130263241160314, 0.00029768585693351087, 0.000213846501098376, 0.00034843225100228707, 0.00015992647552933993]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 280.
Rec Success! in episode: 280.
total combined:  26
-----
It has processed 281 episodes
----target item:  596
[2.564551639702315e-05, 1.4697981874755121e-05, 0.00029042169443537446, 0.00010137528175441491, 0.0003374068609558317, 0.9981939787120476, 0.0003026059723627609, 0.00021640558001623537, 0.0003556852361480868, 0.00016177716400798993]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 281.
Rec Success! in episode: 281.
total combined:  26
-----
It has processed 282 episodes
----target item:  367
[2.2091956819477262e-05, 0.9980931734206362, 0.0002801038373996183, 9.816317787853055e-05, 0.00032989155378359446, 0.00017014515335575517, 0.00029284149046040884, 0.0002096841292898152, 0.0003453041664752008, 0.00015860111390141333]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 282.
Rec Success! in episode: 282.
total combined:  26
-----
It has processed 283 episodes
----target item:  1993
[2.5897942976470942e-05, 1.496562459996583e-05, 0.00029983324973562736, 0.00010470912412341287, 0.00035257012214439434, 0.00018229183442959197, 0.0003123384524591541, 0.998166409559808, 0.00037082574464284356, 0.000170158345080597]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2962799059536163e-05, 7.490802828087925e-06, 0.4996161512463737, 5.241046892971387e-05, 0.00017647330723934932, 9.124324746764268e-05, 0.00015633599168370018, 0.4996161512463737, 0.00018561086563034364, 8.517002441417695e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.644979296983943e-06, 4.995667607681489e-06, 0.3331974262754829, 3.4952899968720885e-05, 0.0001176912548399135, 6.085074540803524e-05, 0.3331974262754829, 0.3331974262754829, 0.00012378515498850953, 5.680047144158408e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.484967905426958e-06, 3.7474634685704904e-06, 0.2499456090451508, 2.6219661923057907e-05, 0.2499456090451508, 4.564674100840108e-05, 0.2499456090451508, 0.2499456090451508, 9.285652743539207e-05, 4.260845765591397e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 283.
Rec Success! in episode: 283.
total combined:  26
-----
It has processed 284 episodes
----target item:  1993
[0.9979404230425615, 1.502477731070005e-05, 0.0003042195608422035, 0.00010616096281904677, 0.00035700736078968497, 0.00018489377505180411, 0.00031591985824391946, 0.00022844809671247835, 0.0003755885769648277, 0.00017231398870391217]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 284.
Rec Success! in episode: 284.
total combined:  26
-----
It has processed 285 episodes
----target item:  1132
[0.9980669885284331, 1.4059609109308331e-05, 0.0002858478044495886, 0.00010041928359225852, 0.0003347876562962565, 0.000172141370076784, 0.00030043012506941237, 0.00021384696750096662, 0.0003515167906122991, 0.00015996186485988862]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 285.
Rec Success! in episode: 285.
total combined:  26
-----
It has processed 286 episodes
----target item:  633
[2.3910594038527454e-05, 0.9979264550068465, 0.0003051976713816474, 0.00010650148275001747, 0.000357524600643967, 0.00018344047485422898, 0.0003207768669114982, 0.00022869902940058541, 0.00037484012625278517, 0.00017265414692028394]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3910594038527454e-05, 0.9979264550068465, 0.0003051976713816474, 0.00010650148275001747, 0.000357524600643967, 0.00018344047485422898, 0.0003207768669114982, 0.00022869902940058541, 0.00037484012625278517, 0.00017265414692028394]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1968342791025716e-05, 0.4995077025066914, 0.0001527653534760665, 0.4995077025066914, 0.00017895736801171893, 9.182032371367865e-05, 0.0001605634513488851, 0.00011447429434127282, 0.0001876245782767251, 8.642127465777235e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.982327929469245e-06, 0.33314840277585844, 0.33314840277585844, 0.33314840277585844, 0.00011935624019186573, 6.12398848587616e-05, 0.0001070883533779817, 7.634902950906477e-05, 0.00012513686627995023, 5.7638970277350116e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.249897458411712, 0.249897458411712, 0.249897458411712, 0.249897458411712, 8.95301337812281e-05, 4.5936559959816764e-05, 8.032788724686672e-05, 5.727005823093406e-05, 9.386623071401949e-05, 4.3235483219377376e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.249897458411712, 0.249897458411712, 0.249897458411712, 0.249897458411712, 8.95301337812281e-05, 4.5936559959816764e-05, 8.032788724686672e-05, 5.727005823093406e-05, 9.386623071401949e-05, 4.3235483219377376e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 286.
Rec Success! in episode: 286.
total combined:  26
-----
It has processed 287 episodes
----target item:  2048
[2.3176507644295997e-05, 0.9980397643447092, 0.0002855541396045584, 0.00010090898791873807, 0.0003376143046182482, 0.00017509272223339506, 0.0003033592273488272, 0.00021726965800513733, 0.00035627691417956304, 0.0001609831937383464]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 287.
Rec Success! in episode: 287.
total combined:  26
-----
It has processed 288 episodes
----target item:  2048
[2.4976752874383516e-05, 1.4526303862020164e-05, 0.0002760721354442113, 9.718493397992438e-05, 0.00032691929967080917, 0.0001695023447963844, 0.9983832307605662, 0.0002083673438599644, 0.00034383034165862863, 0.00015538978328743944]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2500206891591228e-05, 7.270032440109754e-06, 0.49966450820762986, 4.863849947206855e-05, 0.0001636144979810588, 8.483145864560002e-05, 0.49966450820762986, 0.0001042823669193698, 0.00017207802903584755, 7.776849335466153e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318696973823797, 4.84781296015587e-06, 0.33318696973823797, 3.243319064194831e-05, 0.0001091016429866163, 5.6567429105565034e-05, 0.33318696973823797, 6.953771032413971e-05, 0.00011474530632293384, 5.185769294460428e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991857020785374, 0.24991857020785374, 0.24991857020785374, 2.432765194534024e-05, 8.183551308733438e-05, 4.2430383797732567e-05, 0.24991857020785374, 5.215919804243906e-05, 8.606874067380052e-05, 3.889768103829313e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 288.
Rec Success! in episode: 288.
total combined:  26
-----
It has processed 289 episodes
----target item:  2048
[2.276466218717485e-05, 0.9980665904573279, 0.00028257401910161976, 9.994334190171049e-05, 0.00033339785027771605, 0.00017222383871918383, 0.00029915539546075453, 0.00021314916327765348, 0.00035142182090230895, 0.00015877945084390976]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 289.
Rec Success! in episode: 289.
total combined:  26
-----
It has processed 290 episodes
----target item:  2048
[0.9981344182573112, 1.4393491112167644e-05, 0.0002734069719703489, 9.626201617696917e-05, 0.0003229500417354669, 0.00016746325732806206, 0.00029011996641423713, 0.00020673930829458534, 0.0003404754922960751, 0.00015377119736081777]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 290.
Rec Success! in episode: 290.
total combined:  26
-----
It has processed 291 episodes
----target item:  2049
[2.575308274896274e-05, 1.5092943756447766e-05, 0.0002933823080122993, 0.00010284035985654553, 0.00034692792201026075, 0.00017970978956938596, 0.0003116261897808716, 0.00022138308056267393, 0.9983380449457655, 0.0001652393779369047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2889142685611625e-05, 7.553857047681085e-06, 0.49965752198341373, 5.147050102512677e-05, 0.00017363371725247518, 8.99428290717681e-05, 0.00015596557755094068, 0.00011079986584004146, 0.49965752198341373, 8.270054269896104e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318394974476634, 5.03709804460278e-06, 0.33318394974476634, 3.432179857679207e-05, 0.00011578324187615466, 5.997609507086509e-05, 0.00010400169089092804, 7.388408121073116e-05, 0.33318394974476634, 5.514676003094419e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991690656380533, 0.24991690656380533, 0.24991690656380533, 2.574433052549113e-05, 8.684748969385776e-05, 4.498728152832562e-05, 7.801030297160678e-05, 5.541947934358729e-05, 0.24991690656380533, 4.136486071585315e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 291.
Rec Success! in episode: 291.
total combined:  26
-----
It has processed 292 episodes
----target item:  2049
[0.9981088634589098, 1.4168900938944556e-05, 0.0002775575532794582, 9.804682500884507e-05, 0.0003277049892030363, 0.00016925024108305152, 0.000293891084880064, 0.00020943619962990534, 0.0003451087771214265, 0.00015597196994533846]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 292.
Rec Success! in episode: 292.
total combined:  26
-----
It has processed 293 episodes
----target item:  2049
[0.9980482431467078, 1.4681249446669032e-05, 0.00028555656551692795, 0.00010090984518651338, 0.00033761717280541165, 0.00017509420972575384, 0.0003033618045235201, 0.0002172715038097599, 0.000356279940914088, 0.00016098456136383948]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 293.
Rec Success! in episode: 293.
total combined:  26
-----
It has processed 294 episodes
----target item:  2049
[0.9980869000065788, 1.4420793665112795e-05, 0.0002803246737196735, 9.876443593569666e-05, 0.0003313886709804607, 0.0001718351267571209, 0.00029743183579998154, 0.0002120051209881983, 0.00034926737534704723, 0.00015766196022788835]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 294.
Rec Success! in episode: 294.
total combined:  26
-----
It has processed 295 episodes
----target item:  2049
[0.9980914944300558, 1.4259049928538212e-05, 0.0002797929529491823, 9.874802915342651e-05, 0.0003304987441644934, 0.00017093220015793785, 0.00029657604662078146, 0.00021197287718410782, 0.00034834432471637846, 0.00015738134506946094]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 295.
Rec Success! in episode: 295.
total combined:  26
-----
It has processed 296 episodes
----target item:  2049
[2.245231088799896e-05, 0.9980833166893737, 0.000279790660499816, 9.874722007351771e-05, 0.0003304960362634236, 0.0001709307996458456, 0.0002965736166611882, 0.00021197114041024396, 0.0003483414705997253, 0.0001573800555846438]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.245231088799896e-05, 0.9980833166893737, 0.000279790660499816, 9.874722007351771e-05, 0.0003304960362634236, 0.0001709307996458456, 0.0002965736166611882, 0.00021197114041024396, 0.0003483414705997253, 0.0001573800555846438]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1237479623760402e-05, 0.4995450575248847, 0.0001400364471153715, 0.4995450575248847, 0.0001654147090591441, 8.555161148779433e-05, 0.0001484363899466768, 0.00010609248121798419, 0.00017434642685566431, 7.876940492410644e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.4946258454456315e-06, 0.33316218800295383, 0.33316218800295383, 0.33316218800295383, 0.00011032023151439384, 5.7057039482434174e-05, 9.89968606614249e-05, 7.075638651771696e-05, 0.00011627707284209603, 5.253377427500353e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990512328242803, 0.24990512328242803, 0.24990512328242803, 0.24990512328242803, 8.275126064698004e-05, 4.2798513755293434e-05, 7.425759452614532e-05, 5.30744007947637e-05, 8.721949029601835e-05, 3.9405610268622704e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 296.
Rec Success! in episode: 296.
total combined:  26
-----
It has processed 297 episodes
----target item:  2049
[2.575308274896274e-05, 1.5092943756447766e-05, 0.0002933823080122993, 0.00010284035985654553, 0.00034692792201026075, 0.00017970978956938596, 0.0003116261897808716, 0.00022138308056267393, 0.9983380449457655, 0.0001652393779369047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2889142685611625e-05, 7.553857047681085e-06, 0.49965752198341373, 5.147050102512677e-05, 0.00017363371725247518, 8.99428290717681e-05, 0.00015596557755094068, 0.00011079986584004146, 0.49965752198341373, 8.270054269896104e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318394974476634, 5.03709804460278e-06, 0.33318394974476634, 3.432179857679207e-05, 0.00011578324187615466, 5.997609507086509e-05, 0.00010400169089092804, 7.388408121073116e-05, 0.33318394974476634, 5.514676003094419e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991690656380533, 0.24991690656380533, 0.24991690656380533, 2.574433052549113e-05, 8.684748969385776e-05, 4.498728152832562e-05, 7.801030297160678e-05, 5.541947934358729e-05, 0.24991690656380533, 4.136486071585315e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 297.
Rec Success! in episode: 297.
total combined:  26
-----
It has processed 298 episodes
----target item:  2049
[2.5526901086757794e-05, 1.4964264023544153e-05, 0.00029319162402789386, 0.00010345920677930914, 0.0003463831704325989, 0.00017909969266327225, 0.00031074029912247337, 0.00022158625075184568, 0.9983401028647568, 0.0001649457263554352]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2775926802892898e-05, 7.489445787962897e-06, 0.49965798963389546, 5.1780169022690255e-05, 0.00017336087980912573, 8.963738121246442e-05, 0.00015552202371940945, 0.00011090142553972724, 0.49965798963389546, 8.25534803149385e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331841325314212, 4.994145094791547e-06, 0.3331841325314212, 3.4528279455305785e-05, 0.00011560126236830454, 5.977239175850309e-05, 0.00010370587809563446, 7.395177507724055e-05, 0.3331841325314212, 5.5048673886584134e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991700135265066, 0.24991700135265066, 0.24991700135265066, 2.5899204736355718e-05, 8.671097457182515e-05, 4.4834478756434255e-05, 7.778840450590874e-05, 5.547024623168901e-05, 0.24991700135265066, 4.129128059505549e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 298.
Rec Success! in episode: 298.
total combined:  26
-----
It has processed 299 episodes
----target item:  2049
[2.245231088799896e-05, 0.9980833166893737, 0.000279790660499816, 9.874722007351771e-05, 0.0003304960362634236, 0.0001709307996458456, 0.0002965736166611882, 0.00021197114041024396, 0.0003483414705997253, 0.0001573800555846438]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.245231088799896e-05, 0.9980833166893737, 0.000279790660499816, 9.874722007351771e-05, 0.0003304960362634236, 0.0001709307996458456, 0.0002965736166611882, 0.00021197114041024396, 0.0003483414705997253, 0.0001573800555846438]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1237479623760402e-05, 0.4995450575248847, 0.0001400364471153715, 0.4995450575248847, 0.0001654147090591441, 8.555161148779433e-05, 0.0001484363899466768, 0.00010609248121798419, 0.00017434642685566431, 7.876940492410644e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.4946258454456315e-06, 0.33316218800295383, 0.33316218800295383, 0.33316218800295383, 0.00011032023151439384, 5.7057039482434174e-05, 9.89968606614249e-05, 7.075638651771696e-05, 0.00011627707284209603, 5.253377427500353e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990512328242803, 0.24990512328242803, 0.24990512328242803, 0.24990512328242803, 8.275126064698004e-05, 4.2798513755293434e-05, 7.425759452614532e-05, 5.30744007947637e-05, 8.721949029601835e-05, 3.9405610268622704e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 299.
Rec Success! in episode: 299.
total combined:  26
-----
It has processed 300 episodes
----target item:  2049
[0.9980914944300558, 1.4259049928538212e-05, 0.0002797929529491823, 9.874802915342651e-05, 0.0003304987441644934, 0.00017093220015793785, 0.00029657604662078146, 0.00021197287718410782, 0.00034834432471637846, 0.00015738134506946094]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 300.
Rec Success! in episode: 300.
total combined:  26
-----
It has processed 301 episodes
----target item:  2049
[0.9980914944300558, 1.4259049928538212e-05, 0.0002797929529491823, 9.874802915342651e-05, 0.0003304987441644934, 0.00017093220015793785, 0.00029657604662078146, 0.00021197287718410782, 0.00034834432471637846, 0.00015738134506946094]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 301.
Rec Success! in episode: 301.
total combined:  26
-----
It has processed 302 episodes
----target item:  2050
[2.4163373418906608e-05, 1.4201474154483983e-05, 0.0002810760357326028, 9.95661296875873e-05, 0.00033224913698604567, 0.00017089965909883404, 0.0002975330961648376, 0.00021153629212043016, 0.9984109958254979, 0.00015777897713834264]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2092994143968863e-05, 7.1073827651698445e-06, 0.4996727119378435, 4.982965757204778e-05, 0.00016628004700565389, 8.552980334572806e-05, 0.00014890578095949972, 0.00010586713607826215, 0.4996727119378435, 7.896332244248834e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319052699389606, 4.739327468754897e-06, 0.33319052699389606, 3.3227289523109425e-05, 0.00011087845136773337, 5.7032772792268036e-05, 9.929298607866556e-05, 7.059406291060086e-05, 0.33319052699389606, 5.265412817075035e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499205512662296, 0.2499205512662296, 0.2499205512662296, 2.492322512773676e-05, 8.316804183894882e-05, 4.2779313520958454e-05, 7.447798123655769e-05, 5.295140674591711e-05, 0.2499205512662296, 3.949496661145385e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 302.
Rec Success! in episode: 302.
total combined:  26
-----
It has processed 303 episodes
----target item:  2050
[2.2924337492756316e-05, 0.9980544085967442, 0.00028317921752217274, 0.00010004822945368462, 0.00033518787796282524, 0.00017372888741682438, 0.0003016477395098647, 0.00021550178306350057, 0.0003535476478475297, 0.00015982568298676637]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2924337492756316e-05, 0.9980544085967442, 0.00028317921752217274, 0.00010004822945368462, 0.00033518787796282524, 0.00017372888741682438, 0.0003016477395098647, 0.00021550178306350057, 0.0003535476478475297, 0.00015982568298676637]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1473904483254588e-05, 0.49953814180883904, 0.00014173457769581626, 0.49953814180883904, 0.0001677655328929568, 8.695338134995595e-05, 0.00015097829334520519, 0.0001078612141189672, 0.00017695481681700463, 7.999466161848914e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.652348923819851e-06, 0.33315948964510994, 0.33315948964510994, 0.33315948964510994, 0.0001118887120736541, 5.7992256704501646e-05, 0.00010069271382609812, 7.193642294911781e-05, 0.00011801736749775052, 5.335124269519299e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990363462334708, 0.24990363462334708, 0.24990363462334708, 0.24990363462334708, 8.392795849914567e-05, 4.350011385208594e-05, 7.552981664137875e-05, 5.3959662310494733e-05, 8.852507583615221e-05, 4.001887947242123e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 303.
Rec Success! in episode: 303.
total combined:  26
-----
It has processed 304 episodes
----target item:  2050
[0.9980869000065788, 1.4420793665112795e-05, 0.0002803246737196735, 9.876443593569666e-05, 0.0003313886709804607, 0.0001718351267571209, 0.00029743183579998154, 0.0002120051209881983, 0.00034926737534704723, 0.00015766196022788835]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 304.
Rec Success! in episode: 304.
total combined:  26
-----
It has processed 305 episodes
----target item:  2050
[2.276466218717485e-05, 0.9980665904573279, 0.00028257401910161976, 9.994334190171049e-05, 0.00033339785027771605, 0.00017222383871918383, 0.00029915539546075453, 0.00021314916327765348, 0.00035142182090230895, 0.00015877945084390976]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.276466218717485e-05, 0.9980665904573279, 0.00028257401910161976, 9.994334190171049e-05, 0.00033339785027771605, 0.00017222383871918383, 0.00029915539546075453, 0.00021314916327765348, 0.00035142182090230895, 0.00015877945084390976]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1393915018572226e-05, 0.49954116696506984, 0.0001414307989122778, 0.49954116696506984, 0.00016686857648953287, 8.619955641793761e-05, 0.0001497299246174412, 0.00010668304377622549, 0.0001758897333995419, 7.947052122874441e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.5989842760047e-06, 0.3331607675497902, 0.3331607675497902, 0.3331607675497902, 0.00011129025333577967, 5.7489376807776975e-05, 9.985991127375304e-05, 7.115050189951702e-05, 0.0001173067656056, 5.300155743120513e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990434363087802, 0.24990434363087802, 0.24990434363087802, 0.24990434363087802, 8.347896997876775e-05, 4.3122859520812676e-05, 7.490505489418238e-05, 5.337008798177004e-05, 8.799196399302205e-05, 3.9756540119268745e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 305.
Rec Success! in episode: 305.
total combined:  26
-----
It has processed 306 episodes
----target item:  2050
[2.3204707609060617e-05, 0.9980368908364434, 0.0002864336528561168, 0.00010032698990550358, 0.00033783415067403105, 0.00017518451572898493, 0.0003048434100340023, 0.00021722263889654202, 0.00035664763512943687, 0.000161411462722957]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3204707609060617e-05, 0.9980368908364434, 0.0002864336528561168, 0.00010032698990550358, 0.00033783415067403105, 0.00017518451572898493, 0.0003048434100340023, 0.00021722263889654202, 0.00035664763512943687, 0.000161411462722957]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1614336525472877e-05, 0.49953382349385894, 0.0001433647384202524, 0.49953382349385894, 0.0001690915301252679, 8.768272171350126e-05, 0.0001525791236570099, 0.00010872349143975473, 0.00017850798748224477, 8.078908291872827e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.7460387036965e-06, 0.33315793132930455, 0.33315793132930455, 0.33315793132930455, 0.00011277351348868889, 5.847891134793658e-05, 0.00010176076736119649, 7.251179357910554e-05, 0.00011905370374999877, 5.388128385569882e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990277540011935, 0.24990277540011935, 0.24990277540011935, 0.24990277540011935, 8.459175472724887e-05, 4.386520888131543e-05, 7.633106043413602e-05, 5.439131643168873e-05, 8.930254450217652e-05, 4.0416514545923976e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 306.
Rec Success! in episode: 306.
total combined:  26
-----
It has processed 307 episodes
----target item:  2050
[0.9980813471662974, 1.4627576450768957e-05, 0.00028145270885453905, 9.947383331412791e-05, 0.0003319869516937384, 0.00017152181616836404, 0.00029863208874940204, 0.00021241175249819423, 0.00035045877330936587, 0.00015808733266382103]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 307.
Rec Success! in episode: 307.
total combined:  26
-----
It has processed 308 episodes
----target item:  940
[2.2904858077688486e-05, 0.9980459509399212, 0.00028892254603022906, 0.00010068021343025691, 0.0003375389471999288, 0.0001751709586519227, 0.000300167401870908, 0.00021332585785841435, 0.00035530800369799176, 0.00016003027326126968]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 308.
Rec Success! in episode: 308.
total combined:  26
-----
It has processed 309 episodes
----target item:  1919
[2.3248394711047672e-05, 0.9980367857855352, 0.0002884167974570122, 0.00010062396877909856, 0.0003379940722474326, 0.00017575735974870274, 0.00030287815146395555, 0.00021585627699591704, 0.00035599370958162407, 0.0001624454834796867]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 309.
Rec Success! in episode: 309.
total combined:  26
-----
It has processed 310 episodes
----target item:  1349
[2.6235065835039645e-05, 1.533295639533265e-05, 0.000305367370386853, 0.00010536700029213547, 0.9982671648318033, 0.00018448246307281344, 0.0003208788240612825, 0.0002275232034583762, 0.0003747499543475864, 0.00017289833034721616]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.3130914649305892e-05, 7.67429908560539e-06, 0.4996427689959779, 5.273724473912032e-05, 0.4996427689959779, 9.233533058901045e-05, 0.0001606030828362118, 0.00011387765459152628, 0.00018756612605092782, 8.653735550244176e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 310.
Rec Success! in episode: 310.
total combined:  26
-----
It has processed 311 episodes
----target item:  230
[2.5720895386319194e-05, 1.5097302874880254e-05, 0.000301023614701965, 0.00010518337448525169, 0.9982837399987845, 0.00018241015232299228, 0.0003164375924714797, 0.000228908510148949, 0.00037135574330639004, 0.00017012281551733255]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2873432375265218e-05, 7.556273010310676e-06, 0.49964583367641063, 5.264478697574065e-05, 0.49964583367641063, 9.129716229633622e-05, 0.0001583785434561533, 0.0001145698149797932, 0.00018586534320900623, 8.51472908760783e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 311.
Rec Success! in episode: 311.
total combined:  26
-----
It has processed 312 episodes
----target item:  808
[2.3870427336183794e-05, 1.4324684505371706e-05, 0.0002713783155661609, 0.9982417460871766, 0.0003128891608019853, 0.0001635149435437902, 0.00028420686287720286, 0.00020308070825725264, 0.00033309498165463435, 0.00015189382828074356]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995660174231716, 7.168730036829187e-06, 0.00013581017309063353, 0.4995660174231716, 0.0001565841065747972, 8.183038773476853e-05, 0.00014223016736018024, 0.00010163091359103796, 0.00016669602735119244, 7.601464791750301e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331719969158675, 4.780989936106806e-06, 9.057490900500395e-05, 0.3331719969158675, 0.00010442952013011045, 5.457455619303693e-05, 0.3331719969158675, 6.777997951935857e-05, 0.00011117339125069717, 5.069590636321846e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24992621712055665, 3.586420046953587e-06, 0.24992621712055665, 0.24992621712055665, 7.833694056954074e-05, 4.0938651827342014e-05, 0.24992621712055665, 5.0844590885769347e-05, 8.339579969791588e-05, 3.802911474596897e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.1999533498969351, 0.1999533498969351, 0.1999533498969351, 0.1999533498969351, 6.267343165523565e-05, 3.2752948720032575e-05, 0.1999533498969351, 4.0678190503098484e-05, 6.672076946968896e-05, 3.0425174976355007e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.1666429732465056, 0.1666429732465056, 0.1666429732465056, 0.1666429732465056, 0.1666429732465056, 2.729661073500334e-05, 0.1666429732465056, 3.390158061977036e-05, 5.560570706844691e-05, 2.5356622543300004e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([8], dtype=torch.int32)
[0.14284654358806273, 0.14284654358806273, 0.14284654358806273, 0.14284654358806273, 0.14284654358806273, 2.339868534028212e-05, 0.14284654358806273, 2.9060472934209362e-05, 0.14284654358806273, 2.1735725286295633e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.1249944440005386, 0.1249944440005386, 0.1249944440005386, 0.1249944440005386, 0.1249944440005386, 0.1249944440005386, 0.1249944440005386, 2.5428670274859546e-05, 0.1249944440005386, 1.9019325416397464e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 312.
Rec Success! in episode: 312.
total combined:  26
-----
It has processed 313 episodes
----target item:  72
[0.9980028332798178, 1.4984637887083643e-05, 0.0002946282145714446, 0.00010273543221596728, 0.0003450108490711857, 0.0001806180780569022, 0.00030845878754459015, 0.00022046726007361763, 0.0003638276345707349, 0.00016643582619076577]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2131]
random_location_list [2131]
Random Combined Rec Success! in episode: 313.
Random Combined Rec Success! in episode: 313.
Rec Success! in episode: 313.
total combined:  27
-----
It has processed 314 episodes
----target item:  1363
[0.9981363079023066, 1.4696857326412705e-05, 0.0002750496750183712, 9.571816210765629e-05, 0.00032176578619392773, 0.00016730164309401333, 0.0002889537347618199, 0.00020662127010817103, 0.00033815805019962947, 0.00015542691888344615]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 314.
Rec Success! in episode: 314.
total combined:  27
-----
It has processed 315 episodes
----target item:  1135
[2.206993410110858e-05, 0.9981853983646678, 0.00026611430547431936, 9.290477616892956e-05, 0.00031194952800907966, 0.0001621224985143774, 0.0002790813028329888, 0.00019967111846257515, 0.00033106303594987284, 0.00014962513581870572]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 315.
Rec Success! in episode: 315.
total combined:  27
-----
It has processed 316 episodes
----target item:  156
[0.9980849447271761, 1.4918162073607065e-05, 0.00028301589624472005, 9.981338289197285e-05, 0.00033205918338771213, 0.00017187982613458888, 0.0002959764214786387, 0.00020990086327565377, 0.00034843126775083627, 0.0001590602695861199]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 316.
Rec Success! in episode: 316.
total combined:  27
-----
It has processed 317 episodes
----target item:  1839
[0.9979692033760558, 1.4594561254942674e-05, 0.000301852878985885, 0.00010571971257325353, 0.0003530877147045469, 0.00018059316092473027, 0.00031387631602171145, 0.0002256269911135231, 0.000366295330852089, 0.000169149957513543]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9979692033760558, 1.4594561254942674e-05, 0.000301852878985885, 0.00010571971257325353, 0.0003530877147045469, 0.00018059316092473027, 0.00031387631602171145, 0.0002256269911135231, 0.000366295330852089, 0.000169149957513543]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995182161025736, 7.305084343491091e-06, 0.0001510878403124809, 0.4995182161025736, 0.00017673265345292258, 9.03931436764521e-05, 0.0001571059877655687, 0.0001129341383725533, 0.00018334352364277322, 8.466542328676668e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331527060230445, 4.872111843586666e-06, 0.3331527060230445, 0.3331527060230445, 0.00011787150066291801, 6.028753196771499e-05, 0.00010478153402472656, 7.532120468950248e-05, 0.00012228060772231613, 5.646743995574476e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 317.
Rec Success! in episode: 317.
total combined:  27
-----
It has processed 318 episodes
----target item:  1839
[2.234375855241148e-05, 0.9980098257508639, 0.0002943359080488161, 0.00010306622126382107, 0.00034364474797083766, 0.00017651552872255245, 0.00030661442107281055, 0.0002205307654091916, 0.0003572917794013163, 0.0001658311186940334]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.234375855241148e-05, 0.9980098257508639, 0.0002943359080488161, 0.00010306622126382107, 0.00034364474797083766, 0.00017651552872255245, 0.00030661442107281055, 0.0002205307654091916, 0.0003572917794013163, 0.0001658311186940334]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1183584241775247e-05, 0.4995277287043375, 0.00014732214436179018, 0.4995277287043375, 0.00017200239517270948, 8.835023350344558e-05, 0.00015346783307595489, 0.00011038090959816102, 0.00017883305999997687, 8.300243137126067e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.458803778444533e-06, 0.3331561000256116, 0.3331561000256116, 0.3331561000256116, 0.00011471564815718386, 5.8924495156067346e-05, 0.00010235416736440868, 7.361768175389703e-05, 0.00011927130647936975, 5.535782047578767e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 8.604865549879478e-05, 4.4199493840433995e-05, 7.677626050055522e-05, 5.5220910465337376e-05, 8.946587259021425e-05, 4.152411723950912e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 8.604865549879478e-05, 4.4199493840433995e-05, 7.677626050055522e-05, 5.5220910465337376e-05, 8.946587259021425e-05, 4.152411723950912e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 8.604865549879478e-05, 4.4199493840433995e-05, 7.677626050055522e-05, 5.5220910465337376e-05, 8.946587259021425e-05, 4.152411723950912e-05]
[-1, 0, 0, 1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 8.604865549879478e-05, 4.4199493840433995e-05, 7.677626050055522e-05, 5.5220910465337376e-05, 8.946587259021425e-05, 4.152411723950912e-05]
[-1, 0, 0, 1, -1, -1, -1, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 8.604865549879478e-05, 4.4199493840433995e-05, 7.677626050055522e-05, 5.5220910465337376e-05, 8.946587259021425e-05, 4.152411723950912e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 0.24990169117246633, 8.604865549879478e-05, 4.4199493840433995e-05, 7.677626050055522e-05, 5.5220910465337376e-05, 8.946587259021425e-05, 4.152411723950912e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  27
-----
It has processed 319 episodes
----target item:  1839
[2.5863518695493335e-05, 1.5254918666286145e-05, 0.00030972043491907226, 0.00010860523549193426, 0.0003624245492953767, 0.00018564103239900485, 0.9982104870157378, 0.00023139158027988356, 0.00037626896121408415, 0.0001743427533009725]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2945347000269602e-05, 7.635473653875821e-06, 0.49962966315091933, 5.435967456872237e-05, 0.00018140267792960776, 9.291804453166535e-05, 0.49962966315091933, 0.0001158173539699292, 0.00018833215718617799, 8.726296932121431e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.333171574589133, 5.091616786626267e-06, 0.333171574589133, 3.6249045454980123e-05, 0.00012096602803632313, 6.196119543648268e-05, 0.333171574589133, 7.723130356904488e-05, 0.00012558686159619298, 5.819018172123651e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499099541163937, 0.2499099541163937, 0.2499099541163937, 2.7190186610573554e-05, 9.073587551243014e-05, 4.647671256956431e-05, 0.2499099541163937, 5.7930726998817655e-05, 9.420193441721712e-05, 4.364809831664778e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 319.
Rec Success! in episode: 319.
total combined:  27
-----
It has processed 320 episodes
----target item:  1839
[0.997865983758955, 1.5120516441710554e-05, 0.00031765685249682973, 0.00011122069922313, 0.00037040738028823065, 0.0001898294993417563, 0.00032962173008551314, 0.00023684313843176685, 0.0003850558259285259, 0.00017826059880751824]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 320.
Rec Success! in episode: 320.
total combined:  27
-----
It has processed 321 episodes
----target item:  165
[2.547213055657297e-05, 1.4559614259508955e-05, 0.00028938255118649096, 0.0001010742350956086, 0.9983619684305736, 0.00017444493045365387, 0.00029996541394726765, 0.00021599547269835886, 0.00035486104596907364, 0.0001622761752598315]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2579080320187582e-05, 7.207100188575658e-06, 0.49967526997969075, 4.844600541530505e-05, 0.49967526997969075, 8.41203734176573e-05, 0.00014432096025967597, 0.00010410747407631099, 0.00017065017865189975, 7.802886828889646e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331917723978503, 4.805814155617522e-06, 0.3331917723978503, 3.230460136755903e-05, 0.3331917723978503, 5.609286270048436e-05, 9.623561427211644e-05, 6.942059351618341e-05, 0.00011379237457028305, 5.203094586696784e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499212644207419, 0.2499212644207419, 0.2499212644207419, 2.423111099738689e-05, 0.2499212644207419, 4.207426573050208e-05, 7.218463477686195e-05, 5.207116125210435e-05, 8.535365063002168e-05, 3.902749364576949e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2154]
random_location_list [2154]
Random Combined Rec Success! in episode: 321.
Random Combined Rec Success! in episode: 321.
Rec Success! in episode: 321.
total combined:  28
-----
It has processed 322 episodes
----target item:  184
[0.9980591955759959, 1.417440481438078e-05, 0.0002874837150345094, 0.00010108132214940629, 0.00033923478955757606, 0.00017232937086254416, 0.0002978882056300879, 0.00021444341001444425, 0.0003517013376075239, 0.00016246786833373346]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 322.
Rec Success! in episode: 322.
total combined:  28
-----
It has processed 323 episodes
----target item:  1439
[2.532131550643945e-05, 1.502227088370274e-05, 0.000286133894521802, 0.00010092432130202856, 0.0003348467027728687, 0.00017354590457034492, 0.9983324660246283, 0.00021485677631758986, 0.0003543040361005189, 0.0001625787533963868]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 323.
Rec Success! in episode: 323.
total combined:  28
-----
It has processed 324 episodes
----target item:  1168
[2.5188153758326218e-05, 1.5093847957878331e-05, 0.0002959407216838115, 0.9980775428167337, 0.0003450663192988824, 0.00017920517015309335, 0.00030812787523893363, 0.0002217347413652525, 0.0003652989762051316, 0.00016680137760495116]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49952522039147773, 7.554280508542686e-06, 0.00014811459819516584, 0.49952522039147773, 0.00017270134012934164, 8.968992716075305e-05, 0.0001542141148202834, 0.00011097544108280085, 0.00018282752969541136, 8.348198545232149e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331565158325514, 5.038299711625078e-06, 9.878448867900569e-05, 0.3331565158325514, 0.00011518252614354979, 5.981836835932777e-05, 0.3331565158325514, 7.401466389455055e-05, 0.0001219361511794345, 5.567800437840249e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991904551402436, 3.7795060132511314e-06, 0.24991904551402436, 0.24991904551402436, 8.640475459936217e-05, 4.4873051596215644e-05, 0.24991904551402436, 5.552247449923674e-05, 9.147102058101348e-05, 4.1767136613260386e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.1999487903785812, 0.1999487903785812, 0.1999487903785812, 0.1999487903785812, 6.912848970580408e-05, 3.590087489652922e-05, 0.1999487903785812, 4.442099077369048e-05, 7.318177725211272e-05, 3.341597446573846e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664070300501443, 0.16664070300501443, 0.16664070300501443, 0.16664070300501443, 0.16664070300501443, 2.9920396217078405e-05, 0.16664070300501443, 3.7021204862962704e-05, 6.099093065458618e-05, 2.7849438178770642e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.14284173049761234, 0.14284173049761234, 0.14284173049761234, 0.14284173049761234, 0.14284173049761234, 0.14284173049761234, 0.14284173049761234, 3.173398138852719e-05, 5.228044482684885e-05, 2.3872090498335017e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 324.
Rec Success! in episode: 324.
total combined:  28
-----
It has processed 325 episodes
----target item:  165
[2.5523163716582875e-05, 1.528200959874986e-05, 0.0002980324314824244, 0.9980644235215655, 0.00034661693519348385, 0.00018008286152648787, 0.0003126189026710438, 0.00022362351772935878, 0.00036590674407652223, 0.00016788991243988122]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[1.2775374152201651e-05, 7.649262943634205e-06, 0.00014917726751893952, 0.4995715492043456, 0.00017349577363362403, 9.013874455168906e-05, 0.0001564783854000997, 0.4995715492043456, 0.00018315110196759403, 8.403568114113941e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[8.788574055627752e-06, 5.24064903677004e-06, 0.3331740931461137, 0.3331740931461137, 0.00011722889068416875, 6.092974554188601e-05, 0.00010557807947671877, 0.3331740931461137, 0.00012352741505498784, 5.642720780862985e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.24991206417051304, 3.930982166125507e-06, 0.24991206417051304, 0.24991206417051304, 8.793274943634905e-05, 4.570306872893326e-05, 7.91935397018219e-05, 0.24991206417051304, 9.265723810194698e-05, 4.232573981269548e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2154]
random_location_list [2154]
Random Combined Rec Success! in episode: 325.
Random Combined Rec Success! in episode: 325.
Rec Success! in episode: 325.
total combined:  29
-----
It has processed 326 episodes
----target item:  1692
[2.5828758262336937e-05, 1.5150581168493732e-05, 0.00030043073967356493, 0.0001044172325462034, 0.9982935905961601, 0.0001824205478850818, 0.00031588428428505215, 0.0002236575642085816, 0.00036818239977250226, 0.00017043729603801513]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2927350694329798e-05, 7.582899417724723e-06, 0.4996481522828969, 5.226105606572926e-05, 0.4996481522828969, 9.130188808963932e-05, 0.00015810078364219312, 0.000111941106056963, 0.00018427610622998746, 8.530424400965288e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 326.
Rec Success! in episode: 326.
total combined:  29
-----
It has processed 327 episodes
----target item:  503
[2.33920671992223e-05, 0.9979791467015917, 0.0002989516167024161, 0.00010388794577578523, 0.00034559040520234076, 0.0001803342631536934, 0.00031141925872224275, 0.00022340085933630858, 0.00036603260004596183, 0.00016784428227024835]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.33920671992223e-05, 0.9979791467015917, 0.0002989516167024161, 0.00010388794577578523, 0.00034559040520234076, 0.0001803342631536934, 0.00031141925872224275, 0.00022340085933630858, 0.00036603260004596183, 0.00016784428227024835]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1708472336651186e-05, 0.4995202489884613, 0.00014963477594121135, 0.4995202489884613, 0.0001729789703775392, 9.026302436219027e-05, 0.00015587522662259716, 0.0001118192231257883, 0.00018321093794109548, 8.401139237029942e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.808924775280164e-06, 0.3331532872883552, 0.3331532872883552, 0.3331532872883552, 0.00011536772078755792, 6.0200609180003865e-05, 0.00010396043856339277, 7.457744073803696e-05, 0.0001221918958557949, 5.603110503430988e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2499001742085169, 0.2499001742085169, 0.2499001742085169, 0.2499001742085169, 8.653798303330737e-05, 4.515681908466538e-05, 7.798131580583611e-05, 5.594096214434142e-05, 9.165683553589665e-05, 4.202925032839431e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 327.
Rec Success! in episode: 327.
total combined:  29
-----
It has processed 328 episodes
----target item:  890
[2.1637061150619104e-05, 0.9981677331722336, 0.00026921187143899995, 9.427261488389518e-05, 0.000316155712854538, 0.00016252558542194153, 0.0002802875684743479, 0.00020433916623357272, 0.00033142793896653145, 0.00015240930834202476]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 328.
Rec Success! in episode: 328.
total combined:  29
-----
It has processed 329 episodes
----target item:  1276
[2.4093385164880406e-05, 1.4007581433903221e-05, 0.00028170832302927296, 9.702255380169127e-05, 0.9984041480446763, 0.00017032329169203812, 0.000295131223384114, 0.00020955511240234356, 0.00034477620433595173, 0.00015923428007950504]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2058012405003965e-05, 7.010371914873535e-06, 0.4996711553791275, 4.855686111768368e-05, 0.4996711553791275, 8.524166903193652e-05, 0.00014770427353051895, 0.00010487601171804875, 0.00017255008876432097, 7.969195326272775e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 329.
Rec Success! in episode: 329.
total combined:  29
-----
It has processed 330 episodes
----target item:  1801
[0.9980112966353448, 1.4528373937514846e-05, 0.00029283538834857777, 0.00010214921293967682, 0.00034377502253711177, 0.0001772410979002573, 0.00030917393137582996, 0.0002193248753063966, 0.0003638176125961671, 0.00016585784971371245]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 330.
Rec Success! in episode: 330.
total combined:  29
-----
It has processed 331 episodes
----target item:  461
[2.3066721035697727e-05, 0.9980017697950258, 0.00029423794739690256, 0.00010413453823536825, 0.00034354133132638456, 0.00017643047061413898, 0.0003081111720611699, 0.0002196104469475112, 0.00036152731151176056, 0.0001675702658455997]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 331.
Rec Success! in episode: 331.
total combined:  29
-----
It has processed 332 episodes
----target item:  986
[2.4762862611732852e-05, 1.4768365243188172e-05, 0.00028827858312284975, 0.00010081336882494125, 0.0003361721550079452, 0.0001745009853593126, 0.9983277451313359, 0.00021621553389316583, 0.00035602116345158477, 0.00016072185114938178]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2393580320269071e-05, 7.391428192708227e-06, 0.4996536664293392, 5.045614489242552e-05, 0.00016825100836907481, 8.733610535770758e-05, 0.4996536664293392, 0.0001082138453784884, 0.00017818525079819482, 8.04397780125148e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331821252692633, 4.928797524134548e-06, 0.3331821252692633, 3.3645476292186146e-05, 0.00011219417030943106, 5.8237997939191425e-05, 0.3331821252692633, 7.215982071025807e-05, 0.00011881858283326546, 5.36393466016678e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499158597604517, 0.2499158597604517, 0.2499158597604517, 2.5237062545945947e-05, 8.415548256177316e-05, 4.3683613921179134e-05, 0.2499158597604517, 5.412620385439343e-05, 8.912437382496454e-05, 4.023422148505438e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 332.
Rec Success! in episode: 332.
total combined:  29
-----
It has processed 333 episodes
----target item:  997
[2.3422399945765183e-05, 0.9980251370466925, 0.00029222092124593077, 0.00010188198655110061, 0.00034026904113744434, 0.00017618346472582358, 0.0003027600207461161, 0.00021735459593916272, 0.0003585408437592138, 0.00016222967925707274]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3422399945765183e-05, 0.9980251370466925, 0.00029222092124593077, 0.00010188198655110061, 0.00034026904113744434, 0.00017618346472582358, 0.0003027600207461161, 0.00021735459593916272, 0.0003585408437592138, 0.00016222967925707274]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1723373200869076e-05, 0.49953126803994763, 0.0001462623354054379, 0.49953126803994763, 0.00017031136720374249, 8.818329947339246e-05, 0.000151537362598546, 0.00010879026278345203, 0.00017945676484376318, 8.119915459524959e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.818787807178592e-06, 0.33315743864280156, 0.33315743864280156, 0.33315743864280156, 0.00011358748190476622, 5.881297941348709e-05, 0.00010106634521621116, 7.255658978151036e-05, 0.0001196869144089104, 5.4154973063169405e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990251182687123, 0.24990251182687123, 0.24990251182687123, 0.24990251182687123, 8.520235104377937e-05, 4.411581306221589e-05, 7.581020442942038e-05, 5.442494128258634e-05, 8.977755581697475e-05, 4.062182688021155e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 333.
Rec Success! in episode: 333.
total combined:  29
-----
It has processed 334 episodes
----target item:  1526
[2.3869099658563772e-05, 0.9980444414788283, 0.000289399482240114, 0.00010145883836904113, 0.0003367450084259276, 0.00017358279018109726, 0.000300519362103448, 0.0002152948423642819, 0.0003537961834376528, 0.00016089291439143889]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 334.
Rec Success! in episode: 334.
total combined:  29
-----
It has processed 335 episodes
----target item:  1816
[2.265632493036582e-05, 0.9980215694839001, 0.0002933408376409836, 0.00010128564019910296, 0.00034135813821989727, 0.00017624531298989225, 0.00030357418531065287, 0.0002176140920793613, 0.0003596154899380866, 0.00016274049479144968]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 335.
Rec Success! in episode: 335.
total combined:  29
-----
It has processed 336 episodes
----target item:  1816
[2.324703039898558e-05, 0.9980008462899689, 0.00029640262049002646, 0.00010220040216714238, 0.0003451417780528476, 0.00017809862029597665, 0.00030646133742857044, 0.00021946838954157628, 0.0003634246387538484, 0.00016470889290230058]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 336.
Rec Success! in episode: 336.
total combined:  29
-----
It has processed 337 episodes
----target item:  517
[2.2936782783364877e-05, 0.9980211282839914, 0.00029310795522142266, 0.0001008574475855545, 0.00034198241405092913, 0.00017424252541503558, 0.00030467382752529253, 0.00021783462013149984, 0.0003590634575967268, 0.00016417268569905776]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 337.
Rec Success! in episode: 337.
total combined:  29
-----
It has processed 338 episodes
----target item:  1539
[2.368924508005547e-05, 0.9979430769413475, 0.00030279603667694114, 0.00010389510847863526, 0.0003550397876956253, 0.00018475909636127315, 0.000317289533147815, 0.00022823881080785406, 0.0003714723579678059, 0.00016974308243634714]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.368924508005547e-05, 0.9979430769413475, 0.00030279603667694114, 0.00010389510847863526, 0.0003550397876956253, 0.00018475909636127315, 0.000317289533147815, 0.00022823881080785406, 0.0003714723579678059, 0.00016974308243634714]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1857433418801183e-05, 0.4995112149246212, 0.0001515617670483108, 0.4995112149246212, 0.00017771189539385384, 9.247946383340546e-05, 0.00015881635320452844, 0.000114242834399945, 0.0001859370670801479, 8.496333637856702e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.908331662673495e-06, 0.33314969752098955, 0.33314969752098955, 0.33314969752098955, 0.00011852519508551661, 6.167930665511011e-05, 0.00010592278701782426, 7.619441683611773e-05, 0.00012401098474843855, 5.6666415025666905e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2498981730394749, 0.2498981730394749, 0.2498981730394749, 0.2498981730394749, 8.890666847792001e-05, 4.626612649552964e-05, 7.945350440348515e-05, 5.7154023265935547e-05, 9.302160186865695e-05, 4.250591758895002e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 338.
Rec Success! in episode: 338.
total combined:  29
-----
It has processed 339 episodes
----target item:  88
[2.516524737911493e-05, 1.4944882491103608e-05, 0.00029318918501253233, 0.9980911203404482, 0.00034459462420688555, 0.0001798361035126043, 0.00030544579931925564, 0.00021974135307034875, 0.0003615179604564303, 0.00016444450410359033]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[1.259602977638628e-05, 7.480402716754683e-06, 0.00014675078090419186, 0.49957726550261267, 0.00017248088532182863, 9.001385444730397e-05, 0.00015288561742852084, 0.49957726550261267, 0.000180951568884112, 8.230985529555918e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[8.40054250778275e-06, 4.988829187688655e-06, 0.33317800364716016, 0.33317800364716016, 0.0001150309291616896, 6.003202786893421e-05, 0.00010196245569731927, 0.33317800364716016, 0.00012068019631953153, 5.489407777647885e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[6.301622899376843e-06, 3.7423440475532e-06, 0.2499317318383247, 0.2499317318383247, 8.62898481461556e-05, 4.50327108236672e-05, 0.2499317318383247, 0.2499317318383247, 9.05276162728656e-05, 4.117850451157774e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[5.4824252198926155e-06, 3.2344569389247304e-06, 0.19996767665525494, 0.19996767665525494, 0.19996767665525494, 3.891487515506236e-05, 0.19996767665525494, 0.19996767665525494, 7.831997410850461e-05, 3.5664992302774566e-05]
[0, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[4.568958920327414e-06, 2.6955408037110458e-06, 0.16664962373149717, 0.16664962373149717, 0.16664962373149717, 0.16664962373149717, 0.16664962373149717, 0.16664962373149717, 6.527051988679443e-05, 2.9722591406064293e-05]
[0, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[3.615062715611421e-06, 0.14284499440976345, 0.14284499440976345, 0.14284499440976345, 0.14284499440976345, 0.14284499440976345, 0.14284499440976345, 0.14284499440976345, 5.59471233092819e-05, 2.5476945631053864e-05]
[0, 0, 0, 1, 0, 1, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2136]
random_location_list [2136]
Random Combined Rec Success! in episode: 339.
Random Combined Rec Success! in episode: 339.
Rec Success! in episode: 339.
total combined:  30
-----
It has processed 340 episodes
----target item:  1763
[2.2847629111057546e-05, 0.9980733982538176, 0.0002835933514696282, 9.740418264713523e-05, 0.0003308697609893097, 0.0001734180459082119, 0.00029911601748931055, 0.000211872028166246, 0.000349411681059861, 0.00015806904934177572]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 340.
Rec Success! in episode: 340.
total combined:  30
-----
It has processed 341 episodes
----target item:  570
[2.5099342783692098e-05, 1.488210548154225e-05, 0.00029153086783421874, 0.00010037472597441438, 0.9983454726068968, 0.00017679133247424785, 0.00030510082631076454, 0.00021719664585534635, 0.0003600177215437371, 0.00016353382484528316]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2561894481110046e-05, 7.448300153793241e-06, 0.4996589189869212, 5.0236244316332334e-05, 0.4996589189869212, 8.848176156864542e-05, 0.00015269899372446946, 0.00010870409517888349, 0.00018018418523295, 8.184655150148095e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2188]
random_location_list [2188]
Random Combined Rec Success! in episode: 341.
Random Combined Rec Success! in episode: 341.
Rec Success! in episode: 341.
total combined:  31
-----
It has processed 342 episodes
----target item:  985
[2.5412760469635794e-05, 1.4830273862646065e-05, 0.0002993297112952627, 0.00010474558540243776, 0.9982983091043406, 0.0001818011621854075, 0.00031383312719153667, 0.00022458148562249573, 0.00036798763659290254, 0.000169169153036945]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2719105831253086e-05, 7.422563282365252e-06, 0.49964905858340575, 5.242524469870225e-05, 0.49964905858340575, 9.09916191451886e-05, 0.00015707371746850107, 0.00011240320337436779, 0.00018417809037354479, 8.466928901451964e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 342.
Rec Success! in episode: 342.
total combined:  31
-----
It has processed 343 episodes
----target item:  560
[2.262777092379566e-05, 0.9980385062871031, 0.0002895836892854607, 9.991840700142733e-05, 0.00033859426404111054, 0.00017550353114904993, 0.00030297662778825817, 0.00021577664320875318, 0.00035496961142126736, 0.00016154316807772374]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.262777092379566e-05, 0.9980385062871031, 0.0002895836892854607, 9.991840700142733e-05, 0.00033859426404111054, 0.00017550353114904993, 0.00030297662778825817, 0.00021577664320875318, 0.00035496961142126736, 0.00016154316807772374]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1325558783968775e-05, 0.4995341259943653, 0.00014494123645347946, 0.4995341259943653, 0.00016947180763968002, 8.78423051707844e-05, 0.00015164461491768338, 0.00010799963748520489, 0.00017766792912183815, 8.08549216966313e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.5855773040162305e-06, 0.33316113797252783, 0.33316113797252783, 0.33316113797252783, 0.00011115753078330401, 5.76537737843924e-05, 9.970257484773429e-05, 7.086158994486807e-05, 0.00011662787665049115, 5.299715910165105e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[5.690220263701968e-06, 0.24991641142007254, 0.24991641142007254, 0.24991641142007254, 8.338334826425734e-05, 4.3248214172590934e-05, 7.47905649107898e-05, 0.24991641142007254, 8.7486855704152e-05, 3.975511639426392e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 343.
Rec Success! in episode: 343.
total combined:  31
-----
It has processed 344 episodes
----target item:  1890
[0.9980336729047968, 1.4695665630581758e-05, 0.0002910098495157832, 0.00010019113703454531, 0.00033916479148801617, 0.00017773101961697095, 0.00030261970434305194, 0.00021871200716919655, 0.00035772593413891377, 0.0001644769862662119]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 344.
Rec Success! in episode: 344.
total combined:  31
-----
It has processed 345 episodes
----target item:  1753
[0.9980469814245005, 1.4684072724793414e-05, 0.0002871713203191589, 0.00010107694414715364, 0.00033874366393760923, 0.0001740615037543277, 0.0003042273249782874, 0.00021647578644158554, 0.0003528866078742992, 0.00016369135132246948]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 345.
Rec Success! in episode: 345.
total combined:  31
-----
It has processed 346 episodes
----target item:  159
[2.5504390815765744e-05, 1.5535110347302967e-05, 0.9981779623800558, 0.00010731913891766438, 0.0003655554370135634, 0.00018940850148806696, 0.0003270276763259467, 0.00023300265960551144, 0.0003837741996689906, 0.00017491050576143554]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49955045141276755, 7.774737250497942e-06, 0.49955045141276755, 5.3709184446146145e-05, 0.0001829467193816759, 9.47918166758259e-05, 0.00016366502716966743, 0.00011660904986198313, 0.0001920645234724413, 8.75361162067932e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331352012736776, 0.3331352012736776, 0.3331352012736776, 3.581704294353215e-05, 0.0001220016757290752, 6.321381721924659e-05, 0.00010914329396247157, 7.776307515335619e-05, 0.0001280820655923231, 5.8375208367434116e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24990899411116158, 0.24990899411116158, 0.24990899411116158, 2.686897433784238e-05, 9.15223487183562e-05, 4.7421291460011744e-05, 0.24990899411116158, 5.833575021872492e-05, 9.608369230714028e-05, 4.379149831167248e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2153]
random_location_list [2153]
Random Combined Rec Success! in episode: 346.
Random Combined Rec Success! in episode: 346.
Rec Success! in episode: 346.
total combined:  32
-----
It has processed 347 episodes
----target item:  356
[2.267993062127896e-05, 0.9980233207624721, 0.0002905265037826184, 0.00010228093394274386, 0.00034056592400172537, 0.00017618178439450272, 0.00030304661096686614, 0.0002188222672489482, 0.0003567128647547305, 0.0001658624178144105]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.267993062127896e-05, 0.9980233207624721, 0.0002905265037826184, 0.00010228093394274386, 0.00034056592400172537, 0.00017618178439450272, 0.00030304661096686614, 0.0002188222672489482, 0.0003567128647547305, 0.0001658624178144105]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1351765244549131e-05, 0.4995309128173189, 0.0001454144072718473, 0.4995309128173189, 0.0001704601519342097, 8.818255620833916e-05, 0.00015168097483616018, 0.00010952498266284263, 0.00017854202325500574, 8.301750394932804e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.819708485854949e-06, 0.3331524359557083, 0.3331524359557083, 0.3331524359557083, 0.00011655792785638985, 6.030270183249844e-05, 0.00010388169633151468, 7.492781214490192e-05, 0.0001223204050154796, 5.688188120836778e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[5.86590684944091e-06, 0.2499122773586171, 0.2499122773586171, 0.2499122773586171, 8.743522199148632e-05, 4.523570569911998e-05, 7.792622386689262e-05, 0.2499122773586171, 9.17579092500198e-05, 4.2669597874756126e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 347.
Rec Success! in episode: 347.
total combined:  32
-----
It has processed 348 episodes
----target item:  226
[2.546092626207776e-05, 1.5090308141840179e-05, 0.0002854878727661259, 9.9678716676117e-05, 0.0003375322523240572, 0.0001723952254283352, 0.0003004708988157115, 0.00021507522390674868, 0.9983885260081997, 0.00016028256747918033]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2843166378622397e-05, 7.5884431629127844e-06, 0.4996642427026652, 5.040449992185284e-05, 0.000171218396315758, 8.710663226710072e-05, 0.00015206705735767474, 0.00010888670423748988, 0.4996642427026652, 8.139969502829079e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318692788015164, 5.060138086264074e-06, 0.33318692788015164, 3.361081111079457e-05, 0.00011417213118242089, 5.808458705405492e-05, 0.00010140160400256755, 7.260801028236242e-05, 0.33318692788015164, 5.427907782666074e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991858645996398, 0.24991858645996398, 0.24991858645996398, 2.5210972279212956e-05, 8.563882688847827e-05, 4.356838962446248e-05, 7.605984333878295e-05, 5.446219457314889e-05, 0.24991858645996398, 4.071393343999655e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2162]
random_location_list [2162]
Random Combined Rec Success! in episode: 348.
Random Combined Rec Success! in episode: 348.
Rec Success! in episode: 348.
total combined:  33
-----
It has processed 349 episodes
----target item:  643
[2.6940021679242575e-05, 1.591288267626126e-05, 0.0003071006227279129, 0.00010772261631731779, 0.9982478948721536, 0.00018544654536657858, 0.00032476319581398384, 0.0002306055464399618, 0.0003803764043902959, 0.0001732372924348346]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.348389389554621e-05, 7.96464175618343e-06, 0.49963837654517146, 5.391682107266165e-05, 0.49963837654517146, 9.281883922703826e-05, 0.00016254895878232913, 0.000115421611643199, 0.00019038422233787634, 8.670792094212948e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 349.
Rec Success! in episode: 349.
total combined:  33
-----
It has processed 350 episodes
----target item:  355
[2.2752158612524846e-05, 0.9980685255882368, 0.0002847474641865365, 9.876569757563335e-05, 0.00033273319310031345, 0.00017155651665919701, 0.00029723482432984316, 0.0002132135804728503, 0.00034993990105181716, 0.00016053107577443805]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2752158612524846e-05, 0.9980685255882368, 0.0002847474641865365, 9.876569757563335e-05, 0.00033273319310031345, 0.00017155651665919701, 0.00029723482432984316, 0.0002132135804728503, 0.00034993990105181716, 0.00016053107577443805]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1387639127115696e-05, 0.4995413572439935, 0.00014251840538473376, 0.4995413572439935, 0.00016653565022852108, 8.586542204151548e-05, 0.00014876842998169768, 0.00010671511889375062, 0.00017514774651592702, 8.034709983960072e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.6957691548848e-06, 0.3331628475440834, 0.3331628475440834, 0.3331628475440834, 0.00010976895432528631, 5.6693248503936695e-05, 9.829627388604225e-05, 7.042709623931305e-05, 0.00011570288557828925, 5.28731400619606e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[5.772869935228837e-06, 0.24991729188000292, 0.24991729188000292, 0.24991729188000292, 8.23415936071485e-05, 4.2527620466772255e-05, 7.373552829369493e-05, 0.24991729188000292, 8.679284632000204e-05, 3.9662021365479075e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 350.
Rec Success! in episode: 350.
total combined:  33
-----
It has processed 351 episodes
----target item:  1695
[2.4928679278005466e-05, 1.4312896268806064e-05, 0.00028647977641678397, 9.953295490782525e-05, 0.998371440297639, 0.00017371237762240233, 0.000299253325633474, 0.00021456746309527123, 0.0003538714318784143, 0.00016190079726012072]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.247628592905406e-05, 7.1633071423911754e-06, 0.4996641584435943, 4.9814175510265075e-05, 0.4996641584435943, 8.69394350363798e-05, 0.00014977007061572117, 0.00010738655629503309, 0.0001771052977577605, 8.102798452468564e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 351.
Rec Success! in episode: 351.
total combined:  33
-----
It has processed 352 episodes
----target item:  599
[0.9980596935197977, 1.4894480260933244e-05, 0.00028558396357735794, 9.96149994847416e-05, 0.0003357878333843419, 0.0001729881189757487, 0.00030075660757314046, 0.00021553211799265286, 0.00035289645998951854, 0.0001622518989640212]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 352.
Rec Success! in episode: 352.
total combined:  33
-----
It has processed 353 episodes
----target item:  529
[0.9980595422173123, 1.4659532207680647e-05, 0.00028507997039973587, 0.00010053651974357435, 0.0003357843287195679, 0.00017251721194390615, 0.00030151758586134864, 0.00021508026818128096, 0.00035205570136421274, 0.00016322666426621632]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2185]
random_location_list [2185]
Random Combined Rec Success! in episode: 353.
Random Combined Rec Success! in episode: 353.
Rec Success! in episode: 353.
total combined:  34
-----
It has processed 354 episodes
----target item:  1768
[0.998157777239752, 1.4059497555882182e-05, 0.0002740135951556099, 9.547315077974558e-05, 0.00031758652787713346, 0.00016501235812826435, 0.00028491272342468296, 0.0002043832009161446, 0.0003345004416565244, 0.00015228126475385042]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 354.
Rec Success! in episode: 354.
total combined:  34
-----
It has processed 355 episodes
----target item:  1994
[2.3077132821301232e-05, 0.9979947640178358, 0.0002945454764777291, 0.00010333799145642696, 0.0003478316925561614, 0.0001764823812147172, 0.0003099218166169644, 0.0002201684869796552, 0.00036421293018111653, 0.0001656580738600128]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 355.
Rec Success! in episode: 355.
total combined:  34
-----
It has processed 356 episodes
----target item:  582
[2.496606869189248e-05, 1.4140231291972049e-05, 0.0002779775119586593, 9.62347307125574e-05, 0.9984316814080064, 0.0001667590055352372, 0.00028895904275367797, 0.00020516298222996785, 0.0003387494166059367, 0.00015536960221368163]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2494568682685941e-05, 7.076648440208121e-06, 0.4996771166608656, 4.816182585199357e-05, 0.4996771166608656, 8.345654551503544e-05, 0.00014461302060510094, 0.00010267627651963718, 0.0001695312107098843, 7.775658194399071e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319257472631836, 4.71882068561135e-06, 0.33319257472631836, 3.211506435672463e-05, 0.33319257472631836, 5.565013956160756e-05, 9.64302407850038e-05, 6.846615903787439e-05, 0.00011304608257903104, 5.18493140389699e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992169951921825, 0.24992169951921825, 0.24992169951921825, 2.4088926563847905e-05, 0.24992169951921825, 4.1742159077652636e-05, 7.233057243796965e-05, 5.135522254766221e-05, 8.479381362369146e-05, 3.889122887618019e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2189]
random_location_list [2189]
Random Combined Rec Success! in episode: 356.
Random Combined Rec Success! in episode: 356.
Rec Success! in episode: 356.
total combined:  35
-----
It has processed 357 episodes
----target item:  179
[2.4810350584641892e-05, 1.51089236875333e-05, 0.00029088155901093205, 9.996281855781252e-05, 0.0003376777118693108, 0.00017486335666022244, 0.9983254717250817, 0.00021505421440012692, 0.00035420123210100417, 0.0001619681080466065]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2796737240529344e-05, 7.764223923496448e-06, 0.4996449974197153, 5.1089567396765624e-05, 0.00017322710477893184, 8.98689567983434e-05, 0.4996449974197153, 0.00011069920207076398, 0.00018167051023832863, 8.288885812235468e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331783601287899, 5.177418783060934e-06, 0.3331783601287899, 3.406806507189898e-05, 0.00011551306026910938, 5.9927332020107667e-05, 0.3331783601287899, 7.381756808128377e-05, 0.0001211433777933358, 5.5272791611591424e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991378798328495, 0.24991378798328495, 0.24991378798328495, 2.5554118184891133e-05, 8.664520241421319e-05, 4.4950898200855206e-05, 0.24991378798328495, 5.5369826695156854e-05, 9.086844782392163e-05, 4.145957354110266e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2156]
random_location_list [2156]
Random Combined Rec Success! in episode: 357.
Random Combined Rec Success! in episode: 357.
Rec Success! in episode: 357.
total combined:  36
-----
It has processed 358 episodes
----target item:  488
[0.9980545590219544, 1.4760754651664144e-05, 0.00028603088272961293, 0.00010119638979813202, 0.00033617681403244897, 0.0001727410342590014, 0.000302192986896549, 0.00021550178834876598, 0.00035486433875801517, 0.00016197598857161798]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 358.
Rec Success! in episode: 358.
total combined:  36
-----
It has processed 359 episodes
----target item:  650
[2.358374805269621e-05, 0.9979751540403214, 0.00029719994725283905, 0.00010390944743442162, 0.00034905440141717517, 0.00018055915922306507, 0.0003128945745189471, 0.0002238142186238325, 0.00036595178744614306, 0.00016787867570931247]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 359.
Rec Success! in episode: 359.
total combined:  36
-----
It has processed 360 episodes
----target item:  837
[2.610119982218789e-05, 1.575227695991289e-05, 0.0003092153365387973, 0.0001070273017994849, 0.998249875479076, 0.00018551619209129287, 0.00032354987025410604, 0.00023054477644178072, 0.0003789381351263927, 0.00017347943188993908]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.306405157214518e-05, 7.884256661951657e-06, 0.4996394014063756, 5.3568809091582014e-05, 0.4996394014063756, 9.285370471316089e-05, 0.00016194168160681176, 0.00011539120307273451, 0.0001896643592504687, 8.682912128008983e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 360.
Rec Success! in episode: 360.
total combined:  36
-----
It has processed 361 episodes
----target item:  1512
[0.997971968745518, 1.57156174300018e-05, 0.00029904711504371055, 0.00010475119514622134, 0.00035179965613507154, 0.00018101454807233322, 0.00031433347723325495, 0.0002257942388477773, 0.0003677211553723561, 0.00016785425120136922]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 361.
Rec Success! in episode: 361.
total combined:  36
-----
It has processed 362 episodes
----target item:  135
[2.4296286158232553e-05, 0.9979932327303584, 0.00029488417759855834, 0.00010295395389156426, 0.0003447877550497624, 0.00017935355830062835, 0.0003086133230130399, 0.0002231625101072619, 0.0003630520665066219, 0.00016566363901590245]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2149]
random_location_list [2149]
Random Combined Rec Success! in episode: 362.
Random Combined Rec Success! in episode: 362.
Rec Success! in episode: 362.
total combined:  37
-----
It has processed 363 episodes
----target item:  1021
[2.2677680260732865e-05, 0.9980244113844161, 0.0002914480454490694, 0.00010066706779548792, 0.000340188952123611, 0.0001769916376929975, 0.0003047976107254339, 0.00021654147305895835, 0.00035809479170652417, 0.0001641813567713106]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 363.
Rec Success! in episode: 363.
total combined:  37
-----
It has processed 364 episodes
----target item:  1504
[0.9980443294532183, 1.448171475450143e-05, 0.0002884232470016154, 9.974788187897503e-05, 0.00034075053745430775, 0.0001745035509595695, 0.00030239969551879286, 0.00021709683784763652, 0.0003558000285182089, 0.00016246705284821795]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 364.
Rec Success! in episode: 364.
total combined:  37
-----
It has processed 365 episodes
----target item:  184
[2.5721904908057188e-05, 1.5143961879408016e-05, 0.0002898085126683936, 0.00010021857958847034, 0.0003369736614679519, 0.00017282987495730856, 0.9983271558391075, 0.0002156239612096219, 0.00035489886023034803, 0.00016162484398302824]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2873585642668541e-05, 7.579418823012518e-06, 0.49965390145232397, 5.015851166274352e-05, 0.00016865233371080583, 8.649982203214124e-05, 0.49965390145232397, 0.00010791788326586934, 0.00017762373696629638, 8.08918032484715e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318233641760797, 5.054155415976211e-06, 0.33318233641760797, 3.344701213869606e-05, 0.00011246180290940872, 5.7680351780713686e-05, 0.33318233641760797, 7.196247719321753e-05, 0.00011844417008180654, 5.3940777656333116e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499160020580683, 0.2499160020580683, 0.2499160020580683, 2.5088195383844026e-05, 8.435622509151876e-05, 4.326532753606422e-05, 0.2499160020580683, 5.3978175408981255e-05, 8.884352565686193e-05, 4.046031864929779e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 365.
Rec Success! in episode: 365.
total combined:  37
-----
It has processed 366 episodes
----target item:  313
[2.5875754743785684e-05, 1.510825441145179e-05, 0.0003017927404794866, 0.00010541557579416074, 0.9982994472802877, 0.00018169612685158627, 0.000312899358244084, 0.00022391865067604037, 0.00036560204925987187, 0.00016824420925192594]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.2950843403139803e-05, 7.5616977713277725e-06, 0.4996499595542429, 5.2760610381417444e-05, 0.4996499595542429, 9.093910918200533e-05, 0.00015660646924841004, 0.00011207152829597023, 0.00018298422344448627, 8.42064097871411e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 366.
Rec Success! in episode: 366.
total combined:  37
-----
It has processed 367 episodes
----target item:  846
[0.9981613621697127, 1.4153961601422422e-05, 0.0002711082017322243, 9.65745533309234e-05, 0.0003164457986420238, 0.00016370939035933565, 0.0002854863406949357, 0.00020397443221505622, 0.000333523530753273, 0.00015366162095800862]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 367.
Rec Success! in episode: 367.
total combined:  37
-----
It has processed 368 episodes
----target item:  1113
[0.9979481918954758, 1.475163577154409e-05, 0.0003051556456588228, 0.00010373754031207338, 0.00035501400764171805, 0.00018420247281310384, 0.00031779045763808414, 0.00022776292542037735, 0.00037338316264563337, 0.00017001025662316007]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 368.
Rec Success! in episode: 368.
total combined:  37
-----
It has processed 369 episodes
----target item:  198
[2.2158231525788755e-05, 0.9980636524263411, 0.00028476693250424704, 9.970094352925109e-05, 0.00033223708042686047, 0.00017323411833694593, 0.00029843063628863173, 0.00021212469559211286, 0.0003520495365787087, 0.00016164539887633883]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 369.
Rec Success! in episode: 369.
total combined:  37
-----
It has processed 370 episodes
----target item:  550
[2.348198100586195e-05, 0.9980015991306075, 0.0002942217170160325, 0.00010311359235720452, 0.0003414844464789497, 0.00017988506094515505, 0.00030672953222808923, 0.00022085042777200014, 0.0003625931488201804, 0.00016604096276917453]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 370.
Rec Success! in episode: 370.
total combined:  37
-----
It has processed 371 episodes
----target item:  1157
[0.9980032961205804, 1.4933850905136634e-05, 0.00029492016392637633, 0.00010130726722911938, 0.0003442683020679099, 0.0001784660056494443, 0.00030970074585182024, 0.00022149383278726584, 0.00036469785715077373, 0.00016691585385185257]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 371.
Rec Success! in episode: 371.
total combined:  37
-----
It has processed 372 episodes
----target item:  390
[2.5739664446674776e-05, 1.5394735092802623e-05, 0.00029241212116417833, 0.00010125915229532175, 0.9983386684377434, 0.00017646512485845045, 0.0003078794752175403, 0.00021986915098391065, 0.00035903235740369633, 0.00016327978079430674]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2882416693458404e-05, 7.704894240628335e-06, 0.49965743549811087, 5.067908311692148e-05, 0.49965743549811087, 8.83188386157615e-05, 0.0001540902640488011, 0.00011004207249397812, 0.00017969171447791024, 8.171972009062232e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 372.
Rec Success! in episode: 372.
total combined:  37
-----
It has processed 373 episodes
----target item:  800
[2.3589712733222526e-05, 0.9980323707273056, 0.00028960619347747355, 9.996128310388067e-05, 0.0003402891836511316, 0.00017543976953408012, 0.0003026231438876776, 0.0002165153259189464, 0.00035706168358563785, 0.00016254297680248173]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 373.
Rec Success! in episode: 373.
total combined:  37
-----
It has processed 374 episodes
----target item:  1716
[2.595091116913664e-05, 1.5308904043236515e-05, 0.0003002211150673247, 0.00010503085018195869, 0.9982926492978782, 0.00018086941124390845, 0.00031580186566247003, 0.0002250453820729301, 0.000368914094426751, 0.00017020816825404585]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2988493251067615e-05, 7.662143172964912e-06, 0.49964786413421636, 5.256819230165202e-05, 0.49964786413421636, 9.052557391741995e-05, 0.00015805959082121956, 0.00011263575321834954, 0.00018464238864122277, 8.518959624329078e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 374.
Rec Success! in episode: 374.
total combined:  37
-----
It has processed 375 episodes
----target item:  797
[2.2671965970010886e-05, 0.9980043540022945, 0.00029463431975560887, 0.00010276397193516776, 0.000341803742951469, 0.00017906407024726167, 0.00030796433658106937, 0.00022162118340178456, 0.00036091277805071355, 0.00016420962881223984]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 375.
Rec Success! in episode: 375.
total combined:  37
-----
It has processed 376 episodes
----target item:  739
[0.9979586105783128, 1.5523328068740946e-05, 0.0003023277413299918, 0.00010396303388821848, 0.00035337701739883144, 0.0001824710961947057, 0.00031630002550281003, 0.00022651318340337315, 0.0003711318745229528, 0.00016978212137715003]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 376.
Rec Success! in episode: 376.
total combined:  37
-----
It has processed 377 episodes
----target item:  561
[0.9980459747876043, 1.4700197906263661e-05, 0.0002899757723900496, 0.00010005145641169516, 0.0003385497239591593, 0.00017336344690952078, 0.00030392980840763276, 0.00021542209029780542, 0.0003553367296798043, 0.00016269598643376036]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 377.
Rec Success! in episode: 377.
total combined:  37
-----
It has processed 378 episodes
----target item:  893
[2.5590539341935226e-05, 1.5130770008948563e-05, 0.0002941032747894071, 0.0001029439831170051, 0.998323422643632, 0.00017873382353265232, 0.0003097797948236319, 0.00022169122110606945, 0.0003624190104302877, 0.00016618493921791773]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.280788980114617e-05, 7.572846835765262e-06, 0.4996540405918529, 5.152275901012507e-05, 0.4996540405918529, 8.945505543888241e-05, 0.00015504266720244535, 0.00011095493892757262, 0.00018138823435522567, 8.317442472286337e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.333182383690249, 5.049772352631647e-06, 0.333182383690249, 3.43567233859604e-05, 0.333182383690249, 5.9650970837673226e-05, 0.00010338650593321556, 7.398765551921653e-05, 0.00012095441923025855, 5.546288199411521e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991602783337452, 0.24991602783337452, 0.24991602783337452, 2.577055768342088e-05, 0.24991602783337452, 4.474346309382037e-05, 7.754895264337176e-05, 5.549723479155179e-05, 9.072642937515433e-05, 4.160202891473018e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 378.
Rec Success! in episode: 378.
total combined:  37
-----
It has processed 379 episodes
----target item:  1127
[2.5549583370429883e-05, 1.523845627385973e-05, 0.0002990674637059158, 0.00010450559926723978, 0.9982927763227367, 0.00018205958718902235, 0.00031575781250692275, 0.00022665405593895016, 0.00036874576520071157, 0.0001696453538101246]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2787619529102605e-05, 7.626879006822181e-06, 0.4996476074455806, 5.230526943296457e-05, 0.4996476074455806, 9.112120142409699e-05, 0.00015803744081218285, 0.00011344082563121915, 0.00018455802116178161, 8.490785184053549e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 379.
Rec Success! in episode: 379.
total combined:  37
-----
It has processed 380 episodes
----target item:  6
[2.6183505416735746e-05, 1.5120370622580299e-05, 0.0002952250063025587, 0.00010446847886368626, 0.00034399258916405624, 0.00017971359447530868, 0.9982804544413741, 0.0002218800290087319, 0.00036566755703120824, 0.0001672944277407624]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3104954446604745e-05, 7.567809010708036e-06, 0.4996435607903052, 5.2286912497959064e-05, 0.00017216973583999905, 8.994740893360983e-05, 0.4996435607903052, 0.00011105188654045668, 0.00018301814830463004, 8.373156381544659e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317778979876456, 5.046449264388884e-06, 0.33317778979876456, 3.486653148079443e-05, 0.0001148081083376209, 5.9979716058430726e-05, 0.33317778979876456, 7.405283488895201e-05, 0.00012204216551645054, 5.58347981595083e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991344254584708, 0.24991344254584708, 0.24991344254584708, 2.615304854882856e-05, 8.611645333310208e-05, 4.499020577613673e-05, 0.24991344254584708, 5.5546316303241865e-05, 9.15426497618219e-05, 4.188114288867579e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2112]
random_location_list [2112]
Random Combined Rec Success! in episode: 380.
Random Combined Rec Success! in episode: 380.
Rec Success! in episode: 380.
total combined:  38
-----
It has processed 381 episodes
----target item:  1709
[0.9980193320057161, 1.4835389015743288e-05, 0.0002920077892057341, 0.00010251756051739863, 0.00034300768723372164, 0.0001769764737217293, 0.00030714615361065594, 0.00021848119739409803, 0.00036120111962294795, 0.00016449462396156574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9980193320057161, 1.4835389015743288e-05, 0.0002920077892057341, 0.00010251756051739863, 0.00034300768723372164, 0.0001769764737217293, 0.00030714615361065594, 0.00021848119739409803, 0.00036120111962294795, 0.00016449462396156574]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.49952997281463696, 7.42542878085889e-06, 0.00014615612977201037, 0.49952997281463696, 0.00017168266704285754, 8.858050167162434e-05, 0.00015373320420046982, 0.00010935450155604604, 0.00018078886819081596, 8.23330695113271e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331568390001013, 4.952320211963138e-06, 0.3331568390001013, 0.3331568390001013, 0.00011450214757049172, 5.907793634019318e-05, 0.00010253092136233248, 7.29329610865273e-05, 0.0001205754431780782, 5.491126994645398e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331568390001013, 4.952320211963138e-06, 0.3331568390001013, 0.3331568390001013, 0.00011450214757049172, 5.907793634019318e-05, 0.00010253092136233248, 7.29329610865273e-05, 0.0001205754431780782, 5.491126994645398e-05]
[-1, 0, 0, -1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331568390001013, 4.952320211963138e-06, 0.3331568390001013, 0.3331568390001013, 0.00011450214757049172, 5.907793634019318e-05, 0.00010253092136233248, 7.29329610865273e-05, 0.0001205754431780782, 5.491126994645398e-05]
[-1, 0, 0, -1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331568390001013, 4.952320211963138e-06, 0.3331568390001013, 0.3331568390001013, 0.00011450214757049172, 5.907793634019318e-05, 0.00010253092136233248, 7.29329610865273e-05, 0.0001205754431780782, 5.491126994645398e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([6], dtype=torch.int32)
[0.24992168161775247, 3.6658081750702167e-06, 0.24992168161775247, 0.24992168161775247, 8.399509674896902e-05, 4.337624519475138e-05, 0.24992168161775247, 5.3564871013779566e-05, 8.843634910543043e-05, 4.023515875208625e-05]
[-1, 0, 0, -1, -1, -1, 1, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 381.
Rec Success! in episode: 381.
total combined:  38
-----
It has processed 382 episodes
----target item:  584
[2.419017636844171e-05, 1.3968590029209277e-05, 0.0002864197315758485, 9.964023626936237e-05, 0.9983757784746446, 0.0001729464675227299, 0.0002991876507484009, 0.00021193542884081232, 0.0003531389353110189, 0.000162794308689621]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.210665392045276e-05, 6.990973635932105e-06, 0.4996652297386187, 4.986775783243384e-05, 0.4996652297386187, 8.655592241956823e-05, 0.00014973687209695658, 0.00010606904436653116, 0.0001767383094083274, 8.147498908258511e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 382.
Rec Success! in episode: 382.
total combined:  38
-----
It has processed 383 episodes
----target item:  620
[2.4946093955720125e-05, 1.4784968586673638e-05, 0.0003002840058794067, 0.00010418981415765579, 0.9982945528977628, 0.00018141457233273648, 0.0003151372311984834, 0.00022605065693230184, 0.00037073641909588585, 0.0001679033400980084]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.24855683242553e-05, 7.399905403569349e-06, 0.4996483565748322, 5.2147203713172295e-05, 0.4996483565748322, 9.079834469863202e-05, 0.00015772679436826568, 0.00011313879146293688, 0.00018555429555936698, 8.403594680535798e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 383.
Rec Success! in episode: 383.
total combined:  38
-----
It has processed 384 episodes
----target item:  1242
[2.6377220972013384e-05, 1.545415519771493e-05, 0.0003112270567367339, 0.00010877479728850716, 0.0003632420822743266, 0.00018687296804181515, 0.00032546953580511165, 0.998102446282887, 0.00038422738027903207, 0.00017590852051765446]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3203191964288777e-05, 7.735620744044085e-06, 0.49960297986969066, 5.444752997294751e-05, 0.0001818218434331839, 9.35397884640823e-05, 0.00016291468931932894, 0.49960297986969066, 0.00019232609322803192, 8.8051503492839e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33315976651730617, 5.158491251642168e-06, 0.33315976651730617, 3.630828298494642e-05, 0.00012124772138417879, 6.237691795373231e-05, 0.00010863950385168608, 0.33315976651730617, 0.0001282524702549798, 5.8717060400287027e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990332292411435, 0.24990332292411435, 0.24990332292411435, 2.7234862908141287e-05, 9.094798206766518e-05, 4.678896024377185e-05, 8.149055120661812e-05, 0.24990332292411435, 9.620224802348903e-05, 4.404369909295584e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 384.
Rec Success! in episode: 384.
total combined:  38
-----
It has processed 385 episodes
----target item:  1245
[0.9980572332803461, 1.458001099645008e-05, 0.0002870642395480086, 9.967683989148218e-05, 0.00033769929673784486, 0.00017347898204776325, 0.00029981465066325144, 0.00021527160344359425, 0.0003543799150062357, 0.00016080118131931053]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 385.
Rec Success! in episode: 385.
total combined:  38
-----
It has processed 386 episodes
----target item:  829
[2.2861313829214677e-05, 0.998022985438076, 0.00028944416781500124, 0.00010135842578688963, 0.0003411905638018213, 0.00017483824798950428, 0.00030632332793164614, 0.00021826365681349596, 0.0003578439595941388, 0.00016489089836212235]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2861313829214677e-05, 0.998022985438076, 0.00028944416781500124, 0.00010135842578688963, 0.0003411905638018213, 0.00017483824798950428, 0.00030632332793164614, 0.00021826365681349596, 0.0003578439595941388, 0.00016489089836212235]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1442547855794376e-05, 0.49953059816992373, 0.00014487263359165835, 0.49953059816992373, 0.00017077274663272998, 8.751006327057936e-05, 0.000153320993071047, 0.0001092453547038727, 0.0001791081065223074, 8.253121450449574e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.631490457001225e-06, 0.33315683193611906, 0.33315683193611906, 0.33315683193611906, 0.00011389513967237773, 5.83639431669772e-05, 0.0001022558708275043, 7.286007385777632e-05, 0.00011945432284160249, 5.504335081953259e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990213535345268, 0.24990213535345268, 0.24990213535345268, 0.24990213535345268, 8.543315304416296e-05, 4.37790032409475e-05, 7.670249570964819e-05, 5.4652602899525224e-05, 8.960311629161222e-05, 4.1288215003340965e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 386.
Rec Success! in episode: 386.
total combined:  38
-----
It has processed 387 episodes
----target item:  6
[0.9980805159145603, 1.4286872193199557e-05, 0.0002852610460652477, 9.953209848948086e-05, 0.0003321740796358519, 0.00017167889070905413, 0.0002971085364858218, 0.00021163998384882078, 0.0003494456924803784, 0.00015835688553180404]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2112]
random_location_list [2112]
Random Combined Rec Success! in episode: 387.
Random Combined Rec Success! in episode: 387.
Rec Success! in episode: 387.
total combined:  39
-----
It has processed 388 episodes
----target item:  1099
[0.9981249120986482, 1.417868331803537e-05, 0.0002761627979769545, 9.6168222498665e-05, 0.0003257985719476809, 0.00016697516703645797, 0.0002894515629864257, 0.0002070888164653846, 0.00034194960404601484, 0.00015731447507622888]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 388.
Rec Success! in episode: 388.
total combined:  39
-----
It has processed 389 episodes
----target item:  1456
[2.2925109597654277e-05, 0.9980319225596517, 0.00028861929426164066, 0.0001004068697642082, 0.00033974843710833896, 0.0001755159161281927, 0.00030308957908550225, 0.00021776820199918376, 0.00035587917330787773, 0.00016412485909579987]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 389.
Rec Success! in episode: 389.
total combined:  39
-----
It has processed 390 episodes
----target item:  516
[2.5266600429987402e-05, 1.5005232345870624e-05, 0.0002947824757087095, 0.00010188741358347721, 0.9983301149713798, 0.00017686593552026605, 0.0003082616144533343, 0.00021920021150658087, 0.0003627450933342392, 0.00016587045173756056]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2645722535060401e-05, 7.509993493022046e-06, 0.49965588632729696, 5.0993799722357e-05, 0.49965588632729696, 8.851992386908868e-05, 0.00015428236400018828, 0.00010970787550227461, 0.00018155089023433235, 8.301677604988999e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2645722535060401e-05, 7.509993493022046e-06, 0.49965588632729696, 5.0993799722357e-05, 0.49965588632729696, 8.851992386908868e-05, 0.00015428236400018828, 0.00010970787550227461, 0.00018155089023433235, 8.301677604988999e-05]
[0, -1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2645722535060401e-05, 7.509993493022046e-06, 0.49965588632729696, 5.0993799722357e-05, 0.49965588632729696, 8.851992386908868e-05, 0.00015428236400018828, 0.00010970787550227461, 0.00018155089023433235, 8.301677604988999e-05]
[0, -1, -1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2645722535060401e-05, 7.509993493022046e-06, 0.49965588632729696, 5.0993799722357e-05, 0.49965588632729696, 8.851992386908868e-05, 0.00015428236400018828, 0.00010970787550227461, 0.00018155089023433235, 8.301677604988999e-05]
[0, -1, -1, -1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2645722535060401e-05, 7.509993493022046e-06, 0.49965588632729696, 5.0993799722357e-05, 0.49965588632729696, 8.851992386908868e-05, 0.00015428236400018828, 0.00010970787550227461, 0.00018155089023433235, 8.301677604988999e-05]
[0, -1, -1, -1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2645722535060401e-05, 7.509993493022046e-06, 0.49965588632729696, 5.0993799722357e-05, 0.49965588632729696, 8.851992386908868e-05, 0.00015428236400018828, 0.00010970787550227461, 0.00018155089023433235, 8.301677604988999e-05]
[0, -1, -1, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.3331831683686318, 5.007853394513676e-06, 0.3331831683686318, 3.400395396827362e-05, 0.3331831683686318, 5.9027321613766756e-05, 0.00010287937812327335, 7.315598305769888e-05, 0.00012106272033148246, 5.535768361574569e-05]
[0, -1, -1, -1, -1, -1, 1, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 390.
Rec Success! in episode: 390.
total combined:  39
-----
It has processed 391 episodes
----target item:  1162
[0.998040731560879, 1.4815982640711816e-05, 0.0002899270394363006, 0.00010043346154816153, 0.0003401100218957182, 0.00017610513740003546, 0.00030272162108358554, 0.000215883277857081, 0.0003562310288851414, 0.00016304086837441514]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 391.
Rec Success! in episode: 391.
total combined:  39
-----
It has processed 392 episodes
----target item:  809
[2.6230318932127854e-05, 1.5458903850115436e-05, 0.0003123181264722148, 0.00010843295783049989, 0.9982356636418466, 0.00018851772399556472, 0.0003250347773901167, 0.00023115074172995294, 0.00038330189264978466, 0.00017389091530313066]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.312879144788291e-05, 7.737485967524814e-06, 0.4996366181327877, 5.427283187510334e-05, 0.4996366181327877, 9.435683527034202e-05, 0.00016268631032301814, 0.00011569550065511972, 0.000191850149561624, 8.703582932420997e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 392.
Rec Success! in episode: 392.
total combined:  39
-----
It has processed 393 episodes
----target item:  1448
[2.5078879042323408e-05, 1.4778752346198478e-05, 0.0002873279450477444, 9.999237490849651e-05, 0.9983621488316233, 0.00017460970461333333, 0.0003024543442128195, 0.00021706157831338446, 0.0003547522972525775, 0.0001617952926398161]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2551521484663686e-05, 7.39649596286936e-06, 0.49966204388113705, 5.0044359632202555e-05, 0.49966204388113705, 8.738897201850347e-05, 0.00015137288206185188, 0.00010863536042012229, 0.00017754705356587625, 8.097559257967382e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2551521484663686e-05, 7.39649596286936e-06, 0.49966204388113705, 5.0044359632202555e-05, 0.49966204388113705, 8.738897201850347e-05, 0.00015137288206185188, 0.00010863536042012229, 0.00017754705356587625, 8.097559257967382e-05]
[0, -1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 393.
Rec Success! in episode: 393.
total combined:  39
-----
It has processed 394 episodes
----target item:  368
[2.4533407329737784e-05, 1.4564099221960532e-05, 0.000278024678953762, 9.604482281271448e-05, 0.9984147560495062, 0.00016882634317034583, 0.0002913972301087204, 0.00020954596737634282, 0.00034362908396002695, 0.00015867831756002845]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2278142403653202e-05, 7.288840144573488e-06, 0.4996728904356202, 4.80671924522582e-05, 0.4996728904356202, 8.449188712653578e-05, 0.00014583447945969475, 0.0001048706848167553, 0.00017197475956729275, 7.941314278887642e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331906474969306, 4.8603264530817455e-06, 0.3331906474969306, 3.20520470153283e-05, 0.3331906474969306, 5.634067230540543e-05, 9.724498880896188e-05, 6.9929612044949e-05, 0.00011467578607956926, 5.295407650097661e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992064174647907, 0.24992064174647907, 0.24992064174647907, 2.4041695706458753e-05, 0.24992064174647907, 4.2260180724684714e-05, 7.294181332022176e-05, 5.245301346436191e-05, 8.601635809736201e-05, 3.971995277069755e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 394.
Rec Success! in episode: 394.
total combined:  39
-----
It has processed 395 episodes
----target item:  290
[2.321556471643536e-05, 1.3632115785091233e-05, 0.00027099570159814867, 9.433717085175316e-05, 0.9984675612989166, 0.00016361494202763553, 0.0002829017904266715, 0.00020217108852661178, 0.00033082533102419485, 0.00015074499612705366]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1618258741974948e-05, 6.822209596289744e-06, 0.49968435462726657, 4.721115653782193e-05, 0.49968435462726657, 8.188130479481948e-05, 0.00014157855903535897, 0.00010117677710359643, 0.00016556195557532733, 7.544052408176953e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319559828583545, 4.549132241218044e-06, 0.33319559828583545, 3.14809727435229e-05, 0.33319559828583545, 5.459944880580815e-05, 9.44063031899834e-05, 6.746590416026179e-05, 0.00011039872337496618, 5.0304657977879665e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992336882052427, 0.24992336882052427, 0.24992336882052427, 2.361324940150872e-05, 0.24992336882052427, 4.0953956929482695e-05, 7.081228399329512e-05, 5.0604828320062604e-05, 8.280787921960264e-05, 3.7732520038907164e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2168]
random_location_list [2168]
Random Combined Rec Success! in episode: 395.
Random Combined Rec Success! in episode: 395.
Rec Success! in episode: 395.
total combined:  40
-----
It has processed 396 episodes
----target item:  529
[0.9980900782466344, 1.428173648673e-05, 0.00028233389434132025, 9.756370927814264e-05, 0.000329266305646939, 0.00017030909229936227, 0.0002965252048051073, 0.0002122701120278466, 0.0003480777195860998, 0.00015929397889407376]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2185]
random_location_list [2185]
Random Combined Rec Success! in episode: 396.
Random Combined Rec Success! in episode: 396.
Rec Success! in episode: 396.
total combined:  41
-----
It has processed 397 episodes
----target item:  1547
[2.346685860919189e-05, 0.998034437760152, 0.0002895688028736169, 9.886229052656826e-05, 0.00033939500624525674, 0.00017464773235253785, 0.0003040551687902885, 0.00021539052941569817, 0.0003563347041583701, 0.00016384114687628657]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.346685860919189e-05, 0.998034437760152, 0.0002895688028736169, 9.886229052656826e-05, 0.00033939500624525674, 0.00017464773235253785, 0.0003040551687902885, 0.00021539052941569817, 0.0003563347041583701, 0.00016384114687628657]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1745553208679356e-05, 0.49953284280728566, 0.0001449340040934765, 0.49953284280728566, 0.00016987284795981483, 8.741409607839134e-05, 0.0001521846712794124, 0.00010780654394477636, 0.00017835144863197696, 8.200522023227645e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.833565376724044e-06, 0.33315784386044006, 0.33315784386044006, 0.33315784386044006, 0.00011329479647158613, 5.82998539371743e-05, 0.00010149786481930872, 7.190036901846653e-05, 0.00011894950438431683, 5.469246467228938e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990274259286316, 0.24990274259286316, 0.24990274259286316, 0.24990274259286316, 8.498278183001389e-05, 4.3730903114399646e-05, 7.613386643326388e-05, 5.393269209258227e-05, 8.922439595375315e-05, 4.102498912345537e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 397.
Rec Success! in episode: 397.
total combined:  41
-----
It has processed 398 episodes
----target item:  986
[0.9980199161081931, 1.4930588191778022e-05, 0.0002919741581081382, 0.00010227622720181138, 0.00034344687886219403, 0.00017799853707976202, 0.00030548353610333577, 0.0002192010522097302, 0.0003593814074866675, 0.0001653915065636028]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 398.
Rec Success! in episode: 398.
total combined:  41
-----
It has processed 399 episodes
----target item:  122
[2.4000755767457383e-05, 1.402969848592193e-05, 0.00028073557586816874, 9.82304538221474e-05, 0.9984089817163798, 0.00017020505586273746, 0.0002933294300947691, 0.00020792912186179223, 0.00034436232501407617, 0.000158195866842789]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2592349665917654e-05, 7.407175180823472e-06, 0.4996547089004578, 5.139969148497285e-05, 0.4996547089004578, 8.964040730967603e-05, 0.0001553905211009279, 0.00010982739744059243, 0.0001810653365660991, 8.325932033553553e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331826329669068, 4.939295248562456e-06, 0.3331826329669068, 3.4274638540556074e-05, 0.3331826329669068, 5.977453308383392e-05, 0.00010361840294158271, 7.323573819945636e-05, 0.00012073903137806848, 5.5519459887558836e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499161473736483, 0.2499161473736483, 0.2499161473736483, 2.5708979908118226e-05, 0.2499161473736483, 4.483613352336472e-05, 7.772287477763812e-05, 5.4933215989955804e-05, 9.056484514494484e-05, 4.164445606245827e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2143]
random_location_list [2143]
Random Combined Rec Success! in episode: 399.
Random Combined Rec Success! in episode: 399.
Rec Success! in episode: 399.
total combined:  42
-----
It has processed 400 episodes
----target item:  198
[2.2675522789500186e-05, 0.9979966421418407, 0.00029640507015538776, 0.00010228123187145795, 0.00034528485624514955, 0.00017837447978662086, 0.00030927454785957347, 0.00022044572860371392, 0.0003626603643205781, 0.00016595605652751678]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 400.
Rec Success! in episode: 400.
total combined:  42
-----
It has processed 401 episodes
----target item:  580
[2.6797083435338832e-05, 1.5893411417395264e-05, 0.00030566210002141834, 0.00010571139311602037, 0.000358466162083247, 0.0001841411938939871, 0.00031836430848703883, 0.0002278375510145749, 0.998284878904664, 0.00017224789186716323]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3412093183929746e-05, 7.954743114302017e-06, 0.4996472788647, 5.2909155524192115e-05, 0.00017941435980327168, 9.216371839366935e-05, 0.00015934315322668733, 0.00011403399449717717, 0.4996472788647, 8.62110528570154e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.33317951130322543, 5.304456834805531e-06, 0.33317951130322543, 3.5281382140360354e-05, 0.00011963877568964451, 6.145748001282729e-05, 0.00010625470440310135, 7.604122381063254e-05, 0.33317951130322543, 5.7488067432495835e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 401.
Rec Success! in episode: 401.
total combined:  42
-----
It has processed 402 episodes
----target item:  1029
[2.237009466880432e-05, 0.9980262110264182, 0.00029094066760312177, 0.00010151921190328897, 0.0003394221492898301, 0.00017407093449992928, 0.00030538253341000566, 0.00021754002135775173, 0.0003572799420693937, 0.00016526341877968453]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 402.
Rec Success! in episode: 402.
total combined:  42
-----
It has processed 403 episodes
----target item:  179
[2.4774551341931193e-05, 1.4675364099626255e-05, 0.00026964405018806105, 9.419975151838636e-05, 0.00031558698828696634, 0.00016286988407909365, 0.9984315013601206, 0.0002015869709401295, 0.0003325262978481476, 0.00015263478157704176]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3088702053415103e-05, 7.745485451440126e-06, 0.49965190293275297, 5.074575684366011e-05, 0.00016924132749554543, 8.734662739252559e-05, 0.49965190293275297, 0.00010814045604258056, 0.00017798906417568506, 8.189671503923904e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318149556503013, 5.1649006266975586e-06, 0.33318149556503013, 3.3838652588951685e-05, 0.00011285472601105259, 5.824510979821068e-05, 0.33318149556503013, 7.21110010066361e-05, 0.00011868795505069114, 5.46109598271843e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499155497300086, 0.2499155497300086, 0.2499155497300086, 2.538197822045626e-05, 8.465101233443753e-05, 4.3688976813129866e-05, 0.2499155497300086, 5.408961991599323e-05, 8.902644933063104e-05, 4.0963043350738385e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2156]
random_location_list [2156]
Random Combined Rec Success! in episode: 403.
Random Combined Rec Success! in episode: 403.
Rec Success! in episode: 403.
total combined:  43
-----
It has processed 404 episodes
----target item:  184
[2.594792246807157e-05, 1.546495799878975e-05, 0.00030025472011862387, 0.00010303297488798697, 0.0003509115747790304, 0.00018188354082189628, 0.9982568745445511, 0.00022648278429313816, 0.0003707617581878902, 0.00016838522189343538]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2987230158356345e-05, 7.74038727635073e-06, 0.499638913397565, 5.1569175159088724e-05, 0.0001756352321652841, 9.103477974305521e-05, 0.499638913397565, 0.00011335720808244577, 0.00018557047460843786, 8.42787176771796e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.333175697138347, 5.161545383609655e-06, 0.333175697138347, 3.43880258798166e-05, 0.00011711936230267434, 6.0704991928028844e-05, 0.333175697138347, 7.559032296284229e-05, 0.00012374450946090287, 5.6199827041248e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991228672043678, 0.24991228672043678, 0.24991228672043678, 2.579416883416314e-05, 8.785024809341615e-05, 4.553430360732407e-05, 0.24991228672043678, 5.6699665155156954e-05, 9.28197152256025e-05, 4.21550173371118e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 404.
Rec Success! in episode: 404.
total combined:  43
-----
It has processed 405 episodes
----target item:  497
[0.9979470986427433, 1.5411607823833598e-05, 0.00030344124272145226, 0.00010554666016049437, 0.0003545700100591249, 0.00018362206384252514, 0.0003193539156955928, 0.00022645276048373456, 0.0003747625250187983, 0.00016974057145109636]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 405.
Rec Success! in episode: 405.
total combined:  43
-----
It has processed 406 episodes
----target item:  76
[2.621871984546305e-05, 1.5090901727882548e-05, 0.0003144974061115466, 0.00010929936866131992, 0.9982226509098546, 0.00018958768481506613, 0.0003268861383838614, 0.00023477528644884192, 0.0003840205362975209, 0.00017697304785385806]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3123085663113753e-05, 7.553351089447002e-06, 0.49963390417085274, 5.470690355291907e-05, 0.49963390417085274, 9.489309329990224e-05, 0.0001636141970843851, 0.00011751055024081818, 0.00019221130642270104, 8.857917094111628e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2132]
random_location_list [2132]
Random Combined Rec Success! in episode: 406.
Random Combined Rec Success! in episode: 406.
Rec Success! in episode: 406.
total combined:  44
-----
It has processed 407 episodes
----target item:  856
[2.2723042159323723e-05, 0.998083982807165, 0.00028262971748995136, 9.892479185599269e-05, 0.0003279921375899804, 0.00017245154379418704, 0.00029713311992599187, 0.00021057062533250885, 0.00034563954525652647, 0.00015795266943058916]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 407.
Rec Success! in episode: 407.
total combined:  44
-----
It has processed 408 episodes
----target item:  1271
[2.4983081129247713e-05, 1.4742699890613444e-05, 0.0002961251529589233, 0.00010151431264110797, 0.9983222184258703, 0.00017789089980779532, 0.000311815663176172, 0.00022215027511905073, 0.00036311293462424135, 0.00016544655478262888]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2503881312342432e-05, 7.378632311284702e-06, 0.499654244650302, 5.080730075692865e-05, 0.499654244650302, 8.903332164015793e-05, 0.00015606185736313154, 0.00011118487184276583, 0.00018173583210289116, 8.280500206662239e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 408.
Rec Success! in episode: 408.
total combined:  44
-----
It has processed 409 episodes
----target item:  1073
[2.5640990348397424e-05, 1.4605531423943472e-05, 0.0003023043622188565, 0.00010579365244556271, 0.9982886307912846, 0.000182903782242125, 0.0003138761634826133, 0.0002256860982388543, 0.0003699933949454983, 0.0001705652333695092]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2833416329842814e-05, 7.3101258155492245e-06, 0.4996473787563364, 5.295013836988774e-05, 0.4996473787563364, 9.15440610492179e-05, 0.00015709625202670616, 0.00011295677815884532, 0.000185183146676872, 8.536856890024607e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 409.
Rec Success! in episode: 409.
total combined:  44
-----
It has processed 410 episodes
----target item:  884
[2.6871546105187934e-05, 1.5410257429993395e-05, 0.00030133527890560896, 0.00010614718065389223, 0.998290750042379, 0.0001821194004515236, 0.0003150745558726346, 0.00022404921084361588, 0.000369771701258335, 0.00016847082610012732]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3449293528098621e-05, 7.712882418757806e-06, 0.49964766713269043, 5.312699850637506e-05, 0.49964766713269043, 9.115133398896575e-05, 0.00015769580836840112, 0.00011213733625817999, 0.00018507190204614243, 8.432017950408975e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 410.
Rec Success! in episode: 410.
total combined:  44
-----
It has processed 411 episodes
----target item:  685
[2.5864145175444696e-05, 1.4903570024204348e-05, 0.0002814054063589518, 9.674769858549238e-05, 0.0003312583475827773, 0.0001697446127500621, 0.00029687041404532984, 0.0002117480160813508, 0.9984119796635309, 0.00015947812586560703]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2944171671593579e-05, 7.4587568080954476e-06, 0.49967304065436363, 4.8419107255520293e-05, 0.0001657841343556471, 8.495171183353051e-05, 0.0001485740811286544, 0.00010597306242614827, 0.49967304065436363, 7.981366579353547e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.33319086226692207, 4.973631575307793e-06, 0.33319086226692207, 3.2286721083719335e-05, 0.00011054780662930074, 5.664731096918333e-05, 9.907183732975264e-05, 7.066472107559432e-05, 0.33319086226692207, 5.32211705710719e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 411.
Rec Success! in episode: 411.
total combined:  44
-----
It has processed 412 episodes
----target item:  986
[0.9980596702521455, 1.4573864840565698e-05, 0.0002883512080652388, 9.787101786973102e-05, 0.0003337018627443607, 0.00017330401168911348, 0.00030288776140995316, 0.00021585550192782915, 0.0003538940447670878, 0.00015989047454059732]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 412.
Rec Success! in episode: 412.
total combined:  44
-----
It has processed 413 episodes
----target item:  913
[2.273511511457257e-05, 0.9980330002018026, 0.00028880243278634594, 0.00010214899367651328, 0.0003386118943190375, 0.0001737928201818379, 0.0003039055432256213, 0.0002180411953765879, 0.0003544648859572113, 0.00016449691755976531]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 413.
Rec Success! in episode: 413.
total combined:  44
-----
It has processed 414 episodes
----target item:  2021
[2.4457884493375168e-05, 1.4347859520385862e-05, 0.00028905735090487103, 0.00010062826312765812, 0.0003371847912078176, 0.00017601655626916986, 0.000306453982314554, 0.00021705494156583035, 0.9983708488280569, 0.00016394954253935108]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2240682337280009e-05, 7.180816912294019e-06, 0.4996646549138393, 5.03624343892675e-05, 0.00016875424852280045, 8.809276828404681e-05, 0.0001533740929033727, 0.00010863165987082287, 0.4996646549138393, 8.205346910155547e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331869773102675, 4.788320842982694e-06, 0.3331869773102675, 3.358273818075088e-05, 0.00011252890797983923, 5.8742124140272864e-05, 0.00010227309438365378, 7.243789216749351e-05, 0.3331869773102675, 5.4714991502616844e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499185633156629, 0.2499185633156629, 0.2499185633156629, 2.5189909119778437e-05, 8.440624913023938e-05, 4.406158785004504e-05, 7.671351689837577e-05, 5.433457839877288e-05, 0.2499185633156629, 4.104089595143165e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 414.
Rec Success! in episode: 414.
total combined:  44
-----
It has processed 415 episodes
----target item:  2021
[2.2823071926016638e-05, 0.9980306638607845, 0.0002887766564897491, 0.00010086839148954068, 0.00033737702987384616, 0.00017608352279331897, 0.0003061387518950894, 0.0002169317743826117, 0.00035682649595268287, 0.00016351044441253313]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 415.
Rec Success! in episode: 415.
total combined:  44
-----
It has processed 416 episodes
----target item:  2021
[0.9979739091366483, 1.4447567226052756e-05, 0.00029822740358402186, 0.00010418229783932854, 0.0003487572671993847, 0.0001821254878647997, 0.0003157799477864097, 0.0002247443896868689, 0.00036880696509330514, 0.00016901953707153713]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 416.
Rec Success! in episode: 416.
total combined:  44
-----
It has processed 417 episodes
----target item:  2021
[2.3677539483477843e-05, 0.9979111623687626, 0.0003062235847054235, 0.000106908455449361, 0.0003581558515931441, 0.00018713802183474524, 0.00032425771854136914, 0.00023066721999843683, 0.00037890331308407693, 0.00017290592654729958]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 417.
Rec Success! in episode: 417.
total combined:  44
-----
It has processed 418 episodes
----target item:  2021
[2.4844720546709255e-05, 1.4581582792006548e-05, 0.0002952529824672126, 0.00010290576642898128, 0.00034495028733657436, 0.00018023865590154566, 0.00031320491524935724, 0.00022210981488838055, 0.998334397191786, 0.00016751408260329317]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2434551454466636e-05, 7.2979465063367904e-06, 0.49965707633163287, 5.150337856353863e-05, 0.00017264440906290706, 9.020777016501909e-05, 0.00015675614572271127, 0.00011116389562841913, 0.49965707633163287, 8.383923963090488e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331836505870528, 4.866450559696357e-06, 0.3331836505870528, 3.4343721924949284e-05, 0.00011512354610754093, 6.0152763962758834e-05, 0.00010452886060835801, 7.41268248032815e-05, 0.3331836505870528, 5.59060708751522e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991670625996168, 0.24991670625996168, 0.24991670625996168, 2.5760777424307643e-05, 8.635266888237129e-05, 4.5119802894043276e-05, 7.840573361363676e-05, 5.56015634851959e-05, 0.24991670625996168, 4.193441385384996e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 418.
Rec Success! in episode: 418.
total combined:  44
-----
It has processed 419 episodes
----target item:  2021
[2.5233077151729396e-05, 1.4690973708617669e-05, 0.00029966912229454886, 0.00010435068350289097, 0.00035065107903181056, 0.00018328216045686193, 0.0003184303058889014, 0.00022586092510888293, 0.9983086097710105, 0.00016922190184525594]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.262911123087201e-05, 7.352806791669201e-06, 0.49965172300324057, 5.2227335613928846e-05, 0.00017550025522806753, 9.173240255739478e-05, 0.00015937381430611267, 0.00011304300021577985, 0.49965172300324057, 8.469526757488518e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318131344955515, 4.903050888455087e-06, 0.33318131344955515, 3.482660316515447e-05, 0.00011702832764421481, 6.116965270578662e-05, 0.00010627477968215019, 7.538013691174163e-05, 0.33318131344955515, 5.647710033690557e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.249915398180442, 0.249915398180442, 0.249915398180442, 2.6123026850392658e-05, 8.778157694015845e-05, 4.5882639558177263e-05, 7.971546665033646e-05, 5.65417572076604e-05, 0.249915398180442, 4.236281102514928e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 419.
Rec Success! in episode: 419.
total combined:  44
-----
It has processed 420 episodes
----target item:  2022
[2.274431669211496e-05, 0.9980132532633227, 0.00029163759035381865, 0.0001016021943192957, 0.00034041235212922677, 0.00017768632077139093, 0.0003086264756281803, 0.00021902733029744042, 0.00036009189115907296, 0.0001649182653268008]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 420.
Rec Success! in episode: 420.
total combined:  44
-----
It has processed 421 episodes
----target item:  2022
[2.53255162939122e-05, 1.4745933127917773e-05, 0.00030078013819510407, 0.00010522930919937195, 0.00035228068419770745, 0.00018354751133574384, 0.00031954593334969367, 0.9981560113346246, 0.0003724268387851515, 0.00017010680089057332]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2676352069186635e-05, 7.380881706372223e-06, 0.49961378369586473, 5.26711383068305e-05, 0.00017632943503456043, 9.18722780658262e-05, 0.00015994448864962624, 0.49961378369586473, 0.00018641332613580873, 8.514470830236467e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.453979534234161e-06, 4.9223800782520995e-06, 0.3331971752861818, 3.512688215509092e-05, 0.00011759577415720151, 6.12704944050832e-05, 0.3331971752861818, 0.3331971752861818, 0.00012432081686113684, 5.6783814263586816e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.341691572028094e-06, 3.692487795855326e-06, 0.2499454499244142, 2.6350176459794822e-05, 0.2499454499244142, 4.5961618005964325e-05, 0.2499454499244142, 0.2499454499244142, 9.32583611449848e-05, 4.259596736480849e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 421.
Rec Success! in episode: 421.
total combined:  44
-----
It has processed 422 episodes
----target item:  2022
[2.53255162939122e-05, 1.4745933127917773e-05, 0.00030078013819510407, 0.00010522930919937195, 0.00035228068419770745, 0.00018354751133574384, 0.00031954593334969367, 0.9981560113346246, 0.0003724268387851515, 0.00017010680089057332]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2676352069186635e-05, 7.380881706372223e-06, 0.49961378369586473, 5.26711383068305e-05, 0.00017632943503456043, 9.18722780658262e-05, 0.00015994448864962624, 0.49961378369586473, 0.00018641332613580873, 8.514470830236467e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.453979534234161e-06, 4.9223800782520995e-06, 0.3331971752861818, 3.512688215509092e-05, 0.00011759577415720151, 6.12704944050832e-05, 0.3331971752861818, 0.3331971752861818, 0.00012432081686113684, 5.6783814263586816e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.341691572028094e-06, 3.692487795855326e-06, 0.2499454499244142, 2.6350176459794822e-05, 0.2499454499244142, 4.5961618005964325e-05, 0.2499454499244142, 0.2499454499244142, 9.32583611449848e-05, 4.259596736480849e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 422.
Rec Success! in episode: 422.
total combined:  44
-----
It has processed 423 episodes
----target item:  2022
[0.998038943646257, 1.4527137941229357e-05, 0.00028877905221650555, 0.00010086922830615637, 0.000337379828795294, 0.0001760849836039401, 0.0003061412916599306, 0.00021693357407536574, 0.0003568294562293, 0.00016351180091534538]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 423.
Rec Success! in episode: 423.
total combined:  44
-----
It has processed 424 episodes
----target item:  2022
[2.5233731703144974e-05, 1.4795841289381051e-05, 0.00030109651976234416, 0.00010531897548246036, 0.0003520586700631125, 0.00018368132457929282, 0.00031896550423993143, 0.9981561650349751, 0.00037231021844149454, 0.0001703741794638019]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2630411535256383e-05, 7.405863179243119e-06, 0.49961390131106725, 5.2716023870906934e-05, 0.00017621832314631273, 9.193926400066802e-05, 0.00015965397553936866, 0.49961390131106725, 0.00018635496854043173, 8.527854805324914e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.423339063329297e-06, 4.939039115333496e-06, 0.333197163033725, 3.515680719473853e-05, 0.00011752164059653428, 6.131515127189812e-05, 0.333197163033725, 0.333197163033725, 0.0001242818637991638, 5.687305778404764e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.318706551190391e-06, 3.704984279987936e-06, 0.24994542913093992, 2.6372623287531475e-05, 0.24994542913093992, 4.599511489637709e-05, 0.24994542913093992, 0.24994542913093992, 9.322913645975692e-05, 4.266291076549089e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 424.
Rec Success! in episode: 424.
total combined:  44
-----
It has processed 425 episodes
----target item:  2022
[0.997963104238337, 1.460871064682163e-05, 0.00030001655759271946, 0.00010492369061630165, 0.00035060542534678214, 0.00018309679773028525, 0.0003172723793259212, 0.00022567045234616833, 0.0003708924584185382, 0.0001698092896397767]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 425.
Rec Success! in episode: 425.
total combined:  44
-----
It has processed 426 episodes
----target item:  2022
[0.997963104238337, 1.460871064682163e-05, 0.00030001655759271946, 0.00010492369061630165, 0.00035060542534678214, 0.00018309679773028525, 0.0003172723793259212, 0.00022567045234616833, 0.0003708924584185382, 0.0001698092896397767]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 426.
Rec Success! in episode: 426.
total combined:  44
-----
It has processed 427 episodes
----target item:  2022
[2.4665606655604114e-05, 1.4350952136498662e-05, 0.00029065617901187767, 0.00010154251352886255, 0.00033945383140852073, 0.000177184960595546, 0.0003079788390250149, 0.9982200580138413, 0.0003591275206039433, 0.00016498158319286572]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.234558470031627e-05, 7.182912531002967e-06, 0.4996272926846716, 5.082387467525599e-05, 0.00016990281593372517, 8.868429506709567e-05, 0.00015414900984097723, 0.4996272926846716, 0.00017974985516211578, 8.257628274620329e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.233281637882728e-06, 4.790290884036416e-06, 0.33320189480700607, 3.389448813381178e-05, 0.00011330834210030346, 5.9143636844173695e-05, 0.33320189480700607, 0.33320189480700607, 0.00011987534149600988, 5.507019788552508e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.176094913328908e-06, 3.593377763993423e-06, 0.24994730146973454, 2.5425533215083206e-05, 0.24994730146973454, 4.436587143920513e-05, 0.24994730146973454, 0.24994730146973454, 8.992301240377146e-05, 4.1310231326457185e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 427.
Rec Success! in episode: 427.
total combined:  44
-----
It has processed 428 episodes
----target item:  2022
[2.53255162939122e-05, 1.4745933127917773e-05, 0.00030078013819510407, 0.00010522930919937195, 0.00035228068419770745, 0.00018354751133574384, 0.00031954593334969367, 0.9981560113346246, 0.0003724268387851515, 0.00017010680089057332]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2676352069186635e-05, 7.380881706372223e-06, 0.49961378369586473, 5.26711383068305e-05, 0.00017632943503456043, 9.18722780658262e-05, 0.00015994448864962624, 0.49961378369586473, 0.00018641332613580873, 8.514470830236467e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.453979534234161e-06, 4.9223800782520995e-06, 0.3331971752861818, 3.512688215509092e-05, 0.00011759577415720151, 6.12704944050832e-05, 0.3331971752861818, 0.3331971752861818, 0.00012432081686113684, 5.6783814263586816e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.341691572028094e-06, 3.692487795855326e-06, 0.2499454499244142, 2.6350176459794822e-05, 0.2499454499244142, 4.5961618005964325e-05, 0.2499454499244142, 0.2499454499244142, 9.32583611449848e-05, 4.259596736480849e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 428.
Rec Success! in episode: 428.
total combined:  44
-----
It has processed 429 episodes
----target item:  579
[2.567936370573939e-05, 1.4743696222565577e-05, 0.9982506231909153, 0.0001027704668226552, 0.00034937273082266744, 0.00018074081064645345, 0.00031602045249762436, 0.0002228586432382934, 0.0003691224756941358, 0.0001680681694346299]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4995686928414381, 7.378396645538267e-06, 0.4995686928414381, 5.143087976162406e-05, 0.00017484154219069662, 9.0450682844685e-05, 0.00015815058933873024, 0.00011152830612325917, 0.00018472518663847416, 8.410873358067894e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331432253081307, 0.3331432253081307, 0.3331432253081307, 3.429728365636463e-05, 0.0001165951271925357, 6.031809568131867e-05, 0.0001054645700814741, 7.437395526874613e-05, 0.0001231861510823704, 5.608889264512662e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499128195165925, 0.2499128195165925, 0.2499128195165925, 2.5728666258767956e-05, 8.746573475006567e-05, 4.5248602446132495e-05, 0.2499128195165925, 5.579283457624508e-05, 9.241009873131215e-05, 4.207599686753995e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 429.
Rec Success! in episode: 429.
total combined:  44
-----
It has processed 430 episodes
----target item:  459
[2.29948468546035e-05, 0.9980779131229988, 0.00028210543786558114, 9.850803845830994e-05, 0.0003344393842879159, 0.00017117786968063472, 0.0002943780168976277, 0.0002115062965362459, 0.0003483732254888749, 0.00015860376093150376]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.29948468546035e-05, 0.9980779131229988, 0.00028210543786558114, 9.850803845830994e-05, 0.0003344393842879159, 0.00017117786968063472, 0.0002943780168976277, 0.0002115062965362459, 0.0003483732254888749, 0.00015860376093150376]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.150905099226011e-05, 0.49954364423529524, 0.00014119536825438116, 0.49954364423529524, 0.00016738880462772573, 8.567549257265323e-05, 0.00014733786351775314, 0.00010586009845646852, 0.00017436277100871023, 7.93820799793443e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.67575843360562e-06, 0.33316181697099, 0.33316181697099, 0.33316181697099, 0.00011163700896594233, 5.7139757666389206e-05, 9.826438767595897e-05, 7.0601524318209e-05, 0.00011628817275872797, 5.294247721105562e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990494847652517, 0.24990494847652517, 0.24990494847652517, 0.24990494847652517, 8.373901075265315e-05, 4.2860578458255654e-05, 7.370819670303363e-05, 5.295826051591764e-05, 8.72278524769531e-05, 3.97121949926228e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990494847652517, 0.24990494847652517, 0.24990494847652517, 0.24990494847652517, 8.373901075265315e-05, 4.2860578458255654e-05, 7.370819670303363e-05, 5.295826051591764e-05, 8.72278524769531e-05, 3.97121949926228e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 430.
Rec Success! in episode: 430.
total combined:  44
-----
It has processed 431 episodes
----target item:  475
[0.9979841898809337, 1.4992855748180972e-05, 0.0002985995651912713, 0.0001050494041212984, 0.00034911096869392154, 0.00018038342827415336, 0.0003113073020416496, 0.00022352653180135665, 0.0003656898611819662, 0.0001671502020123569]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 431.
Rec Success! in episode: 431.
total combined:  44
-----
It has processed 432 episodes
----target item:  782
[2.5512066245879946e-05, 1.5079294772600428e-05, 0.0002883167365492743, 0.00010285939295446603, 0.998349181752577, 0.00017482889517484403, 0.0003046713658359441, 0.0002195623059213597, 0.0003564923992047614, 0.0001634957907638208]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.276841296107128e-05, 7.546964677915088e-06, 0.49965904404246897, 5.147960943303943e-05, 0.49965904404246897, 8.74992840488078e-05, 0.00015248352598783328, 0.00010988769649897448, 0.00017841918904802818, 8.182723240641084e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 432.
Rec Success! in episode: 432.
total combined:  44
-----
It has processed 433 episodes
----target item:  1632
[0.9979850781031061, 1.4979179148677879e-05, 0.00029754550646047206, 0.00010427322768986202, 0.0003471088732282217, 0.00018142335149073452, 0.00031056124180668264, 0.00022410218764142047, 0.00036664503938366785, 0.00016828329004411766]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 433.
Rec Success! in episode: 433.
total combined:  44
-----
It has processed 434 episodes
----target item:  782
[2.2860925625647085e-05, 1.353600455337727e-05, 0.0002631102812790469, 9.229313510554382e-05, 0.9985072754435239, 0.0001579576528566986, 0.0002745801142753562, 0.00019624376462174417, 0.0003231884336480074, 0.00014895424451070205]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.1440506632877332e-05, 6.773949244725173e-06, 0.49969232631911703, 4.618711602645927e-05, 0.49969232631911703, 7.904822424134214e-05, 0.00013741069237805685, 9.820810091333881e-05, 0.0001617362078581456, 7.454256447114807e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 434.
Rec Success! in episode: 434.
total combined:  44
-----
It has processed 435 episodes
----target item:  1225
[2.32098499758562e-05, 0.9979590108302496, 0.00029984336336457524, 0.00010630552941924163, 0.000352086045089436, 0.0001819092420474375, 0.0003133184433058594, 0.00022463694274076673, 0.0003686902975228919, 0.00017098945628433226]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 435.
Rec Success! in episode: 435.
total combined:  44
-----
It has processed 436 episodes
----target item:  1991
[0.9980877000231287, 1.363356698280797e-05, 0.0002827657969097295, 9.917180517529054e-05, 0.0003338714445701692, 0.00016997782322090442, 0.0002944796239997766, 0.00021029696384645185, 0.00034837930673049875, 0.00015972364543580974]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 436.
Rec Success! in episode: 436.
total combined:  44
-----
It has processed 437 episodes
----target item:  1497
[0.9980988792338746, 1.4232926553030058e-05, 0.00028121560806612563, 9.787357774031432e-05, 0.00032911560584843267, 0.00016904499931599647, 0.0002947659243095088, 0.0002095864296084423, 0.00034623317176569595, 0.00015905252291797457]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9980988792338746, 1.4232926553030058e-05, 0.00028121560806612563, 9.787357774031432e-05, 0.00032911560584843267, 0.00016904499931599647, 0.0002947659243095088, 0.0002095864296084423, 0.00034623317176569595, 0.00015905252291797457]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995487371669783, 7.123583277855273e-06, 0.0001407484817425183, 0.4995487371669783, 0.00016472244253968864, 8.460706417937106e-05, 0.00014753041839070998, 0.00010489806011865098, 0.00017328978853641498, 7.960582725820124e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.333163982676263, 4.750930588346155e-06, 0.333163982676263, 0.333163982676263, 0.00010985831993874224, 5.642697972655143e-05, 9.839244522104543e-05, 6.995965134921778e-05, 0.00011557213903359624, 5.309150535339221e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 437.
Rec Success! in episode: 437.
total combined:  44
-----
It has processed 438 episodes
----target item:  1725
[0.9979953484849361, 1.4603195049051694e-05, 0.0002994780631202738, 0.00010321794634223592, 0.00034514819785345474, 0.0001803947588432747, 0.00030970303835129505, 0.00022128769830427047, 0.0003648789149668667, 0.0001659397022331369]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 438.
Rec Success! in episode: 438.
total combined:  44
-----
It has processed 439 episodes
----target item:  1409
[0.9980896381533362, 1.426965186166733e-05, 0.0002834377555215096, 9.912966751303427e-05, 0.0003299710751929396, 0.0001715595745551862, 0.00029326190628017754, 0.00021229003452773447, 0.00034668767115387107, 0.00015975451005790104]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 439.
Rec Success! in episode: 439.
total combined:  44
-----
It has processed 440 episodes
----target item:  1760
[2.701733375059999e-05, 1.5865606051103628e-05, 0.0003109849706830937, 0.00010763871828861693, 0.0003646062081743014, 0.0001871022487412098, 0.9981942366426034, 0.00023260100842968084, 0.00038432304227058205, 0.000175624221007272]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3522979247156032e-05, 7.94120779471301e-06, 0.49962590947557556, 5.387638051349593e-05, 0.00018249625340679051, 9.365024136652333e-05, 0.49962590947557556, 0.00011642372407648428, 0.00019236511540349663, 8.790514704014943e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317003378646, 5.295506936473583e-06, 0.33317003378646, 3.592687083585105e-05, 0.00012169561618063984, 6.244963179140333e-05, 0.33317003378646, 7.763587786074167e-05, 0.00012827655808641029, 5.861857892860547e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.249909125421681, 0.249909125421681, 0.249909125421681, 2.6948560672415786e-05, 9.12832545643913e-05, 4.684314698571751e-05, 0.249909125421681, 5.8234271903210076e-05, 9.621958517441275e-05, 4.396949397585624e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 440.
Rec Success! in episode: 440.
total combined:  44
-----
It has processed 441 episodes
----target item:  1988
[0.9979193556640541, 1.5131681605517698e-05, 0.0003072618368246544, 0.0001091736893736076, 0.00036039722161413274, 0.00018655259667940433, 0.00031964052380879814, 0.0002296148588224996, 0.0003789043847132674, 0.00017396754250367848]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 441.
Rec Success! in episode: 441.
total combined:  44
-----
It has processed 442 episodes
----target item:  1988
[0.9980618130927715, 1.411873977583681e-05, 0.00028661934081746225, 0.00010151283917283695, 0.00033571188371592676, 0.00017408250146137694, 0.0002977059643473145, 0.00021351342660585375, 0.00035281597789018086, 0.00016210623344162025]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 442.
Rec Success! in episode: 442.
total combined:  44
-----
It has processed 443 episodes
----target item:  1989
[2.4256710895100737e-05, 1.3949105883752839e-05, 0.00028296727534759945, 9.998882840671771e-05, 0.00033141138504132504, 0.00017197272282321155, 0.00029430031313585047, 0.9982726263065287, 0.00034843890411568684, 0.00016008844782214147]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2140558778899152e-05, 6.981570610589002e-06, 0.49963853506158173, 5.004471767646784e-05, 0.00016587242258402145, 8.607287932941583e-05, 0.000147298216387444, 0.49963853506158173, 0.00017439474851168335, 8.012476295786627e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331753408002902, 4.655539963941303e-06, 0.3331753408002902, 3.3371456957491095e-05, 0.00011060916451728368, 5.739621524730036e-05, 9.822327542873128e-05, 0.3331753408002902, 0.00011629213059396936, 5.342981642066352e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991199137808193, 0.24991199137808193, 0.24991199137808193, 2.5031646229885936e-05, 8.296699420426064e-05, 4.305241322951284e-05, 7.3676444070289e-05, 0.24991199137808193, 8.722973875716535e-05, 4.007725118125468e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 443.
Rec Success! in episode: 443.
total combined:  44
-----
It has processed 444 episodes
----target item:  1989
[2.4256710895100737e-05, 1.3949105883752839e-05, 0.00028296727534759945, 9.998882840671771e-05, 0.00033141138504132504, 0.00017197272282321155, 0.00029430031313585047, 0.9982726263065287, 0.00034843890411568684, 0.00016008844782214147]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2140558778899152e-05, 6.981570610589002e-06, 0.49963853506158173, 5.004471767646784e-05, 0.00016587242258402145, 8.607287932941583e-05, 0.000147298216387444, 0.49963853506158173, 0.00017439474851168335, 8.012476295786627e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331753408002902, 4.655539963941303e-06, 0.3331753408002902, 3.3371456957491095e-05, 0.00011060916451728368, 5.739621524730036e-05, 9.822327542873128e-05, 0.3331753408002902, 0.00011629213059396936, 5.342981642066352e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991199137808193, 0.24991199137808193, 0.24991199137808193, 2.5031646229885936e-05, 8.296699420426064e-05, 4.305241322951284e-05, 7.3676444070289e-05, 0.24991199137808193, 8.722973875716535e-05, 4.007725118125468e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 444.
Rec Success! in episode: 444.
total combined:  44
-----
It has processed 445 episodes
----target item:  1989
[0.9979935140239817, 1.4709143370209628e-05, 0.0002965860361862457, 0.000105080155313046, 0.0003478281296810813, 0.00017995580149660913, 0.0003086941193128955, 0.00022084231618634418, 0.0003652314019027737, 0.00016755887256912462]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 445.
Rec Success! in episode: 445.
total combined:  44
-----
It has processed 446 episodes
----target item:  975
[0.9980495406074781, 1.4256606422956485e-05, 0.00028818824073013693, 0.00010058878666281084, 0.00033788479955411936, 0.0001735137458863817, 0.0003027862697101052, 0.00021613836589700025, 0.0003555484861419204, 0.00016155409151651472]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 446.
Rec Success! in episode: 446.
total combined:  44
-----
It has processed 447 episodes
----target item:  1762
[2.2775194424220838e-05, 0.9981500148260816, 0.0002726128364102201, 9.476813767190033e-05, 0.00031931563683422384, 0.00016653587155841758, 0.00028414704868852137, 0.00020294991159394644, 0.0003347251836468311, 0.0001521553530902631]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2775194424220838e-05, 0.9981500148260816, 0.0002726128364102201, 9.476813767190033e-05, 0.00031931563683422384, 0.00016653587155841758, 0.00028414704868852137, 0.00020294991159394644, 0.0003347251836468311, 0.0001521553530902631]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.139868102344447e-05, 0.4995607686426199, 0.00013643908838959805, 0.4995607686426199, 0.0001598132170586673, 8.334898238396323e-05, 0.00014221180778633053, 0.00010157372371475562, 0.00016752548969884933, 7.615172470453276e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.602038194773876e-06, 0.333168375886722, 0.333168375886722, 0.333168375886722, 0.00010658304918006684, 5.558732157476888e-05, 9.484427122014837e-05, 6.774181378326232e-05, 0.00011172653824328277, 5.078730763770667e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2499086249927245, 0.2499086249927245, 0.2499086249927245, 0.2499086249927245, 7.99476336769092e-05, 4.1695887446718915e-05, 7.1142410638407e-05, 5.081293652805832e-05, 8.380574979021778e-05, 3.809541102165454e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 447.
Rec Success! in episode: 447.
total combined:  44
-----
It has processed 448 episodes
----target item:  6
[2.2512452823243665e-05, 0.9980763324340972, 0.0002838255910342472, 9.792426869540615e-05, 0.0003298206640671479, 0.0001706359745594288, 0.00029880757611590016, 0.00021295183336377175, 0.0003481879624536401, 0.00015900124278976378]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2112]
random_location_list [2112]
Random Combined Rec Success! in episode: 448.
Random Combined Rec Success! in episode: 448.
Rec Success! in episode: 448.
total combined:  45
-----
It has processed 449 episodes
----target item:  1797
[2.5060148257574414e-05, 1.5012557798198635e-05, 0.00029545261164915475, 0.00010285029246351119, 0.0003464994750005035, 0.00018076482864008678, 0.9982772874230535, 0.00022383493362015548, 0.0003672146176398595, 0.0001660231118775458]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 449.
Rec Success! in episode: 449.
total combined:  45
-----
It has processed 450 episodes
----target item:  1667
[2.537808838658326e-05, 1.4751905341830184e-05, 0.0002881801663499591, 0.00010158525351792823, 0.9983608264962908, 0.00017458403837457433, 0.0003018716868812195, 0.000214981608186614, 0.00035604267237887766, 0.0001617980842918862]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2701284126579541e-05, 7.383067562096142e-06, 0.49966192587145386, 5.0841621652005483e-05, 0.49966192587145386, 8.737622162800247e-05, 0.00015108143712176696, 0.00010759449041129316, 0.0001781930567103537, 8.09770778800645e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318586618744167, 4.9231963322141625e-06, 0.33318586618744167, 3.390234250679259e-05, 0.33318586618744167, 5.82644395738921e-05, 0.00010074451721424487, 7.17464381985067e-05, 0.00011882315796841677, 5.399734588089941e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991796345356515, 0.24991796345356515, 0.24991796345356515, 2.5429663306414864e-05, 0.24991796345356515, 4.370332465386931e-05, 7.556702467424685e-05, 5.3815979425521337e-05, 8.912755511028119e-05, 4.050263856888891e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 450.
Rec Success! in episode: 450.
total combined:  45
-----
It has processed 451 episodes
----target item:  673
[2.3624703280852845e-05, 0.9979496045967126, 0.00030370100819803657, 0.00010449422211867205, 0.0003539188913958964, 0.00018283598364487292, 0.00031605684846362433, 0.00022492858027044663, 0.00037029672295431517, 0.00017053844296032936]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 451.
Rec Success! in episode: 451.
total combined:  45
-----
It has processed 452 episodes
----target item:  672
[2.6428894424881275e-05, 1.5736674443527888e-05, 0.9982791116044001, 0.00010210186953859041, 0.0003426345543724032, 0.00017654558483339, 0.00030886514973777715, 0.0002203894314552999, 0.00036214576654354156, 0.00016604047025029102]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49957601470628915, 7.875217473591102e-06, 0.49957601470628915, 5.109557485999353e-05, 0.00017146708088375078, 8.834998014063156e-05, 0.0001545676142012745, 0.00011029107247658683, 0.00018123121749167854, 8.309282989432124e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331791843281587, 5.252170754836109e-06, 0.3331791843281587, 3.407686008432522e-05, 0.00011435549439171122, 5.892271336519404e-05, 0.3331791843281587, 7.355575224729544e-05, 0.00012086743046336333, 5.5416594217368195e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991426571699663, 0.24991426571699663, 0.24991426571699663, 2.556070086757582e-05, 8.577687549489949e-05, 4.419731885234402e-05, 0.24991426571699663, 5.517341021532285e-05, 9.066141149922579e-05, 4.1567415084159715e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.19995219666096267, 0.19995219666096267, 0.19995219666096267, 2.045068644641988e-05, 6.862863401860055e-05, 0.19995219666096267, 0.19995219666096267, 4.4143316661734344e-05, 7.253666904386234e-05, 3.325738901599048e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.16663959884565296, 0.16663959884565296, 0.16663959884565296, 1.7043544619457414e-05, 5.719491074947248e-05, 0.16663959884565296, 0.16663959884565296, 0.16663959884565296, 6.0451856158222417e-05, 2.7716614555005094e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 452.
Rec Success! in episode: 452.
total combined:  45
-----
It has processed 453 episodes
----target item:  1670
[2.2614187014497754e-05, 0.9981500523428734, 0.0002713790896152281, 9.508688152107952e-05, 0.0003183443198018822, 0.0001644610266382714, 0.000286379778033742, 0.0002044002358042557, 0.00033509274230421495, 0.00015218939639354242]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 453.
Rec Success! in episode: 453.
total combined:  45
-----
It has processed 454 episodes
----target item:  1141
[0.9979962567808126, 1.4928952761823987e-05, 0.000298599939644755, 0.00010430500846994127, 0.0003457951672256685, 0.000177519346673335, 0.00030926463887159247, 0.00022274857098955947, 0.0003628141652161759, 0.00016776742933500243]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 454.
Rec Success! in episode: 454.
total combined:  45
-----
It has processed 455 episodes
----target item:  1695
[2.6339349923930906e-05, 1.5065195000410075e-05, 0.0003006247639335676, 0.0001027288925624683, 0.9982938519179724, 0.0001812906108072829, 0.0003157360108174381, 0.00022470695558574692, 0.0003710872193803523, 0.00016856908401652782]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.318290250735681e-05, 7.5401631975845515e-06, 0.49964826624560277, 5.141603643411561e-05, 0.49964826624560277, 9.073634902432327e-05, 0.0001580265671206381, 0.00011246632497639729, 0.0001857299686190291, 8.436919691496615e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 455.
Rec Success! in episode: 455.
total combined:  45
-----
It has processed 456 episodes
----target item:  1136
[0.9978797834039219, 1.5420234322204802e-05, 0.0003143549061717633, 0.0001096396802880496, 0.0003669013950692137, 0.00018765604913798317, 0.0003296786837337898, 0.00023438815987897145, 0.0003858662759788814, 0.00017631121149730205]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 456.
Rec Success! in episode: 456.
total combined:  45
-----
It has processed 457 episodes
----target item:  1694
[2.3027720303248906e-05, 0.9979763786736948, 0.0002979709530222743, 0.00010566098865974951, 0.0003474211468193014, 0.00018112353410588928, 0.0003126860913618516, 0.0002241774478109545, 0.0003645053130353253, 0.00016704813118666655]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3027720303248906e-05, 0.9979763786736948, 0.0002979709530222743, 0.00010566098865974951, 0.0003474211468193014, 0.00018112353410588928, 0.0003126860913618516, 0.0002241774478109545, 0.0003645053130353253, 0.00016704813118666655]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.152613134544136e-05, 0.49951999888664783, 0.00014914426163047134, 0.49951999888664783, 0.000173895709939562, 9.065828559505596e-05, 0.00015650967231962138, 0.00011220818535781561, 0.00018244689699325667, 8.361308352335628e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.687311854760554e-06, 0.3331530670653021, 0.3331530670653021, 0.3331530670653021, 0.00011597911844368361, 6.046421758526778e-05, 0.0001043835631704095, 7.483684574212838e-05, 0.0001216823019004764, 5.576544539694107e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990002750256357, 0.24990002750256357, 0.24990002750256357, 0.24990002750256357, 8.699660232489634e-05, 4.535455660240899e-05, 7.829870976990838e-05, 5.613554746442486e-05, 9.12745929652326e-05, 4.182998061865867e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 457.
Rec Success! in episode: 457.
total combined:  45
-----
It has processed 458 episodes
----target item:  1812
[2.2156147653203682e-05, 0.9980864555021068, 0.00028330035650481927, 9.73876981422002e-05, 0.0003306223933955351, 0.00016873319054101364, 0.00029452728441359076, 0.00021173602032692075, 0.00034516077823440607, 0.00015992062868141845]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 458.
Rec Success! in episode: 458.
total combined:  45
-----
It has processed 459 episodes
----target item:  1356
[2.3576476303978923e-05, 0.9979292112217368, 0.0003055047168227497, 0.00010530746205924914, 0.0003546346786400946, 0.00018447889133971508, 0.00032066599617074635, 0.00022965783206866787, 0.0003749899529518933, 0.00017197277190623026]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 459.
Rec Success! in episode: 459.
total combined:  45
-----
It has processed 460 episodes
----target item:  1574
[0.9980342110729598, 1.4849470772155487e-05, 0.0002911336859952481, 0.00010079750779753853, 0.00034039915931172155, 0.00017710699326653874, 0.0003041677112182387, 0.00021588846204084196, 0.00035891266760306763, 0.0001625332690346164]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 460.
Rec Success! in episode: 460.
total combined:  45
-----
It has processed 461 episodes
----target item:  1967
[2.4460251592560116e-05, 1.4065198601949934e-05, 0.000280717085858152, 9.682150526217773e-05, 0.000323715863122823, 0.0001683802131096238, 0.00029205458112783924, 0.00020860338645029925, 0.998432816537769, 0.0001583653771055755]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2241436274680748e-05, 7.03910308219679e-06, 0.4996780859733536, 4.8455523124959145e-05, 0.00016200761854496344, 8.42679659650585e-05, 0.0001461623372955188, 0.0001043981519262316, 0.4996780859733536, 7.925591707909262e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331929494784191, 4.693781023178294e-06, 0.3331929494784191, 3.2310879988012615e-05, 0.0001080291447158833, 5.6191161699138764e-05, 9.746327011977567e-05, 6.961427594455719e-05, 0.3331929494784191, 5.2849051252185826e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992190566824682, 0.24992190566824682, 0.24992190566824682, 2.4235797045114738e-05, 8.103067534102514e-05, 4.214795731885963e-05, 7.310540705955457e-05, 5.221638853107185e-05, 0.24992190566824682, 3.964110171713168e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 461.
Rec Success! in episode: 461.
total combined:  45
-----
It has processed 462 episodes
----target item:  1967
[2.5157682046195383e-05, 1.4539962333369846e-05, 0.00029402570334679823, 0.0001013534961923745, 0.0003398900885289781, 0.00017638226143945637, 0.0003061707139994027, 0.00021876606546157056, 0.9983578130755894, 0.0001659009510625723]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2591030479202846e-05, 7.277026101600141e-06, 0.49966263308769604, 5.072585611777177e-05, 0.00017010972856676672, 8.827659184566165e-05, 0.00015323370351557377, 0.00010948902975178843, 0.49966263308769604, 8.303085822938479e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318615615297814, 4.852482844342492e-06, 0.33318615615297814, 3.382512899355248e-05, 0.00011343295021911282, 5.886479469874452e-05, 0.00010217964139511383, 7.300972005548149e-05, 0.33318615615297814, 5.536682285920736e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991811333968247, 0.24991811333968247, 0.24991811333968247, 2.5371739687944022e-05, 8.508441418045816e-05, 4.4153630520241164e-05, 7.664347010704549e-05, 5.476353430286788e-05, 0.24991811333968247, 4.15298524715185e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 462.
Rec Success! in episode: 462.
total combined:  45
-----
It has processed 463 episodes
----target item:  1136
[2.2509600489260564e-05, 0.9980292392032387, 0.00028987692703161987, 0.00010190660809734883, 0.0003410194207028228, 0.00017417800929517193, 0.0003030595848735857, 0.00021648516811297714, 0.0003588588572340271, 0.00016286662092433193]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 463.
Rec Success! in episode: 463.
total combined:  45
-----
It has processed 464 episodes
----target item:  1956
[2.2389784570185324e-05, 0.9980773159026454, 0.00028394474201173515, 9.85150163363407e-05, 0.00033151977995454497, 0.00016907882252777795, 0.0002969762570850817, 0.00021225959268590054, 0.00034842381813065924, 0.00015957628405241172]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 464.
Rec Success! in episode: 464.
total combined:  45
-----
It has processed 465 episodes
----target item:  1956
[2.5887055233881377e-05, 1.5434695795018104e-05, 0.0002950922897430727, 0.00010209823034076713, 0.9983297692532592, 0.00017563537699068766, 0.00030793426370439984, 0.00022085606367980675, 0.0003613594987759787, 0.00016593327247708804]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2956259234310614e-05, 7.72493889769459e-06, 0.49965587722954663, 5.1099328514122406e-05, 0.49965587722954663, 8.790406844069742e-05, 0.0001541185782482907, 0.00011053665195413402, 0.00018085747106509162, 8.304824455262344e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 465.
Rec Success! in episode: 465.
total combined:  45
-----
It has processed 466 episodes
----target item:  1956
[0.9980793989200983, 1.4917479180777939e-05, 0.000284807622502224, 9.876260585488735e-05, 0.00033256298434976067, 0.00016955647011764283, 0.0002977137119063932, 0.0002130017115009376, 0.00034921563535782554, 0.00016006285913146404]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 466.
Rec Success! in episode: 466.
total combined:  45
-----
It has processed 467 episodes
----target item:  1829
[0.9980346130048575, 1.4921409035672319e-05, 0.0002905039564052329, 0.00010297263569206915, 0.0003409530264309975, 0.00017613731638624816, 0.00030311258667604647, 0.0002167801680086698, 0.00035657584406423255, 0.00016343005244350047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 467.
Rec Success! in episode: 467.
total combined:  45
-----
It has processed 468 episodes
----target item:  1707
[2.3109418184641434e-05, 0.9979432520897834, 0.0003044851897844652, 0.00010600493134195723, 0.00035326789664306935, 0.0001828791832063102, 0.00031685544462532137, 0.00022516392103520463, 0.0003736670729939285, 0.00017131485240167246]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3109418184641434e-05, 0.9979432520897834, 0.0003044851897844652, 0.00010600493134195723, 0.00035326789664306935, 0.0001828791832063102, 0.00031685544462532137, 0.00022516392103520463, 0.0003736670729939285, 0.00017131485240167246]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1521567962963475e-05, 0.49951415092920504, 0.0001514955708472251, 0.49951415092920504, 0.00017589087814643645, 9.110083034775815e-05, 0.00015787906165137152, 0.00011223577399931071, 0.0001861933057887655, 8.538115284611623e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.684310344657572e-06, 0.33315098861777226, 0.33315098861777226, 0.33315098861777226, 0.00011731043021369458, 6.0759703479465705e-05, 0.00010529744827720639, 7.485565523338021e-05, 0.00012418163485888878, 5.694496427597735e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([7], dtype=torch.int32)
[5.764344702189272e-06, 0.24991144945142768, 0.24991144945142768, 0.24991144945142768, 8.799979784574776e-05, 4.557856972837509e-05, 7.898832307739274e-05, 0.24991144945142768, 9.31541956144064e-05, 4.271696332108706e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.1999442457373002, 0.1999442457373002, 0.1999442457373002, 0.1999442457373002, 7.0405150480001e-05, 3.6465607182579766e-05, 6.319542667785225e-05, 0.1999442457373002, 7.452897984574912e-05, 3.417614931276962e-05]
[-1, 1, 0, 0, 1, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 468.
Rec Success! in episode: 468.
total combined:  45
-----
It has processed 469 episodes
----target item:  1160
[2.5257956968824492e-05, 1.4724526808799424e-05, 0.00029565741256318273, 0.00010162222524122688, 0.9983168913787229, 0.0001817580716461517, 0.0003110641224405474, 0.00022145917959520296, 0.0003649774878760504, 0.000166587638137024]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.26414857557276e-05, 7.369554716678656e-06, 0.49965279367778287, 5.086143405968829e-05, 0.49965279367778287, 9.096903904537288e-05, 0.00015568609439804172, 0.00011083925227140692, 0.00018266947401332368, 8.337631017381142e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 469.
Rec Success! in episode: 469.
total combined:  45
-----
It has processed 470 episodes
----target item:  165
[2.5826545732022137e-05, 1.4935754718095808e-05, 0.00030245147637953025, 0.0001048605873891219, 0.00035265467654246895, 0.00018253133790907525, 0.9982497001087264, 0.0002248538398512841, 0.00037192494618266747, 0.00017026072656944763]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([7], dtype=torch.int32)
[1.2926038322421667e-05, 7.475259752643685e-06, 0.00015137523286776447, 5.2482123825907003e-05, 0.00017650164721475742, 9.135588991795348e-05, 0.4996182614910243, 0.4996182614910243, 0.00018614630687761595, 8.521451917246857e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[9.330709975233754e-06, 5.388385445814025e-06, 0.3331894595010211, 3.691447124320122e-05, 0.00012440730863391664, 6.442647679701018e-05, 0.3331894595010211, 0.3331894595010211, 0.0001311647699552095, 5.998937488634795e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[6.4604489939803925e-06, 0.24992020689361774, 0.24992020689361774, 2.7688968025235742e-05, 9.331597812076442e-05, 4.832529346711313e-05, 0.24992020689361774, 0.24992020689361774, 9.838464426051053e-05, 4.4997092661537e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.1999499626310336, 0.1999499626310336, 0.1999499626310336, 2.2152703019705907e-05, 7.465793410641452e-05, 3.8662902623940486e-05, 0.1999499626310336, 0.1999499626310336, 7.871314683942422e-05, 3.600015824254362e-05]
[0, 1, 1, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2154]
random_location_list [2154]
Random Combined Rec Success! in episode: 470.
Random Combined Rec Success! in episode: 470.
Rec Success! in episode: 470.
total combined:  46
-----
It has processed 471 episodes
----target item:  1013
[2.68912309377882e-05, 1.606233703513647e-05, 0.000319683169325729, 0.0001117329697045103, 0.00037396985622640037, 0.00019377914753600256, 0.9981443678437046, 0.00023975554367879024, 0.00039224495680893474, 0.0001815129450419361]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.346025561906156e-05, 8.039913190758496e-06, 0.49961559465183497, 5.5927314624566975e-05, 0.00018718852514696646, 9.69950712004473e-05, 0.49961559465183497, 0.0001200082997862585, 0.00019633602478631194, 9.085529197549208e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331654331453689, 5.361364195440814e-06, 0.3331654331453689, 3.7294768620134674e-05, 0.00012482545926912413, 6.468053690754473e-05, 0.3331654331453689, 8.002675978757351e-05, 0.0001309254103358306, 6.0586264777539214e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990654925649108, 0.24990654925649108, 0.24990654925649108, 2.79747116715751e-05, 9.363126147511353e-05, 4.851670724066022e-05, 0.24990654925649108, 6.0027870232157114e-05, 9.820681935133811e-05, 4.54456040650788e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 471.
Rec Success! in episode: 471.
total combined:  46
-----
It has processed 472 episodes
----target item:  125
[2.5570253918778094e-05, 1.5167007202182634e-05, 0.0003099090841993917, 0.0001076273086715498, 0.0003632158248680573, 0.00018729436244203443, 0.00032407405204564984, 0.0002308119742493524, 0.9982594507530884, 0.0001768793793145915]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3068578416399507e-05, 7.724431175583606e-06, 0.4996381170642429, 5.44936071068312e-05, 0.00018370913707629042, 9.47536686344585e-05, 0.0001640887877245438, 0.00011684383959688592, 0.4996381170642429, 8.908382178328006e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317536111358514, 5.150908344311116e-06, 0.33317536111358514, 3.6338154768655984e-05, 0.00012250337993605922, 6.318490660724254e-05, 0.00010941987658196591, 7.791536938841032e-05, 0.33317536111358514, 5.94040636179211e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499120956672839, 0.2499120956672839, 0.2499120956672839, 2.725695075579415e-05, 9.188877684058052e-05, 4.739447830709872e-05, 8.207494867824925e-05, 5.844367717788661e-05, 0.2499120956672839, 4.455849910475863e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2144]
random_location_list [2144]
Random Combined Rec Success! in episode: 472.
Random Combined Rec Success! in episode: 472.
Rec Success! in episode: 472.
total combined:  47
-----
It has processed 473 episodes
----target item:  136
[2.195290199967438e-05, 0.9982056364500035, 0.0002634747938920082, 9.17404370338797e-05, 0.0003099635844175433, 0.00015861523128531148, 0.00027598288156401864, 0.00019730861375687544, 0.00032719270178373406, 0.00014813240426327383]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 473.
Rec Success! in episode: 473.
total combined:  47
-----
It has processed 474 episodes
----target item:  1049
[2.452190350836198e-05, 1.4682642056696888e-05, 0.0002842975297421165, 9.795470765511423e-05, 0.9984004400506002, 0.00017047459487814834, 0.0002924277111994236, 0.00020823956618286972, 0.00034716299481091434, 0.00015979829936614955]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2272511585550138e-05, 7.348242549190865e-06, 0.49967087438220725, 4.902353049985015e-05, 0.49967087438220725, 8.531766059558211e-05, 0.00014635170848001445, 0.00010421794897275144, 0.00017374515295838985, 7.997447994416643e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 474.
Rec Success! in episode: 474.
total combined:  47
-----
It has processed 475 episodes
----target item:  496
[2.335043310543316e-05, 0.9979915568322547, 0.00029600061228628416, 0.00010224238880271286, 0.0003454601783845938, 0.00017752613833427625, 0.00031011400050980363, 0.00022331777513343457, 0.0003636949002581678, 0.00016673674093087103]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2182]
random_location_list [2182]
Random Combined Rec Success! in episode: 475.
Random Combined Rec Success! in episode: 475.
Rec Success! in episode: 475.
total combined:  48
-----
It has processed 476 episodes
----target item:  1793
[2.513787678766839e-05, 1.4943398503645153e-05, 0.0002892356022434894, 0.9981151811617804, 0.0003391086711321689, 0.00017463711297965718, 0.000303879710279739, 0.00021826363986308112, 0.0003560323881533652, 0.00016358043827657798]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995346353464695, 7.4788413834830055e-06, 0.00014475604000706936, 0.4995346353464695, 0.00016971641106556525, 8.740202353070244e-05, 0.00015208509311229068, 0.00010923613807926354, 0.00017818635819235869, 8.186840169006642e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.333160230030729, 4.987947460252404e-06, 9.654376728781411e-05, 0.333160230030729, 0.00011319086715854304, 5.829201061192404e-05, 0.333160230030729, 7.285408120883189e-05, 0.00011883982387433398, 5.460141021131182e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 476.
Rec Success! in episode: 476.
total combined:  48
-----
It has processed 477 episodes
----target item:  423
[2.609280210835293e-05, 1.5244978689777396e-05, 0.00030152300246405673, 0.9980285032246495, 0.0003542764108121659, 0.0001843385145580609, 0.00031893765370755297, 0.00022902122519761746, 0.0003732257621381545, 0.00016883642567483203]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[1.3060771285333673e-05, 7.630885295114706e-06, 0.00015092756063901083, 0.4995639012909321, 0.00017733331798524464, 9.227077903412503e-05, 0.00015964447712657901, 0.4995639012909321, 0.0001868184297278023, 8.451119704258604e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[8.710589753562435e-06, 5.089248545135846e-06, 0.3331729883916498, 0.3331729883916498, 0.00011826849646636609, 6.153793561260878e-05, 0.00010647131905855782, 0.3331729883916498, 0.00012459437993458784, 5.636285567967047e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[6.5342498982652835e-06, 3.8177003772563536e-06, 0.2499297552858025, 0.2499297552858025, 8.871912612889207e-05, 4.6162689426590527e-05, 0.2499297552858025, 0.2499297552858025, 9.346448833490814e-05, 4.228060262397339e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[5.4884131905501865e-06, 3.2174371167137344e-06, 0.19996745456468484, 0.19996745456468484, 0.19996745456468484, 3.9023511320775524e-05, 0.19996745456468484, 0.19996745456468484, 7.917365725336879e-05, 3.582415769431819e-05]
[0, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[4.57395045280505e-06, 2.6813575155388968e-06, 0.16664948457729456, 0.16664948457729456, 0.16664948457729456, 0.16664948457729456, 0.16664948457729456, 0.16664948457729456, 6.59819829286533e-05, 2.9855245335648686e-05]
[0, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[3.6190125168568624e-06, 0.1428448904812034, 0.1428448904812034, 0.1428448904812034, 0.1428448904812034, 0.1428448904812034, 0.1428448904812034, 0.1428448904812034, 5.655696535205644e-05, 2.5590653706955673e-05]
[0, 0, 0, 1, 0, 1, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2179]
random_location_list [2179]
Random Combined Rec Success! in episode: 477.
Random Combined Rec Success! in episode: 477.
Rec Success! in episode: 477.
total combined:  49
-----
It has processed 478 episodes
----target item:  1675
[2.323718079636911e-05, 0.9980636319079791, 0.00028672219820754786, 9.952935414902222e-05, 0.00033146840478008376, 0.00017226418880075594, 0.00029963208140581084, 0.0002134782173472804, 0.000349371874985994, 0.0001606645915480844]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.323718079636911e-05, 0.9980636319079791, 0.00028672219820754786, 9.952935414902222e-05, 0.00033146840478008376, 0.00017226418880075594, 0.00029963208140581084, 0.0002134782173472804, 0.000349371874985994, 0.0001606645915480844]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1630429579123555e-05, 0.4995403223872932, 0.0001435071820565019, 0.4995403223872932, 0.00016590308322176337, 8.621986179860044e-05, 0.00014996870115074456, 0.00010684787433087968, 0.0001748639400174514, 8.041415325866984e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.756738884050242e-06, 0.33316085329880896, 0.33316085329880896, 0.33316085329880896, 0.00011064654902515224, 5.7503031168436025e-05, 0.0001000193542029212, 7.12605717494834e-05, 0.00011662285676758363, 5.363100177564588e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2499044214490435, 0.2499044214490435, 0.2499044214490435, 0.2499044214490435, 8.299613098500476e-05, 4.313310400494672e-05, 7.502465730380978e-05, 5.345265441258363e-05, 8.747896777085681e-05, 4.022868934860939e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 478.
Rec Success! in episode: 478.
total combined:  49
-----
It has processed 479 episodes
----target item:  235
[0.9979321302554525, 1.4552137391454915e-05, 0.0003072848041977722, 0.00010737857220395642, 0.0003585253502339113, 0.00018562891052105712, 0.0003201540482139171, 0.00022777976203825197, 0.00037530375199689017, 0.0001712624077503367]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9979321302554525, 1.4552137391454915e-05, 0.0003072848041977722, 0.00010737857220395642, 0.0003585253502339113, 0.00018562891052105712, 0.0003201540482139171, 0.00022777976203825197, 0.00037530375199689017, 0.0001712624077503367]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.49950934355711324, 7.283990940243454e-06, 0.00015380968923268777, 0.49950934355711324, 0.0001794578578185294, 9.291551241652059e-05, 0.00016025131731107757, 0.00011401388527514148, 0.00018785619293217856, 8.572443984690907e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331493646930634, 4.858081206031886e-06, 0.3331493646930634, 0.3331493646930634, 0.00011968999597819392, 6.197030011742904e-05, 0.00010688013195754711, 7.604192781482615e-05, 0.00012529129261794686, 5.717419111781055e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331493646930634, 4.858081206031886e-06, 0.3331493646930634, 0.3331493646930634, 0.00011968999597819392, 6.197030011742904e-05, 0.00010688013195754711, 7.604192781482615e-05, 0.00012529129261794686, 5.717419111781055e-05]
[-1, 0, 0, -1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331493646930634, 4.858081206031886e-06, 0.3331493646930634, 0.3331493646930634, 0.00011968999597819392, 6.197030011742904e-05, 0.00010688013195754711, 7.604192781482615e-05, 0.00012529129261794686, 5.717419111781055e-05]
[-1, 0, 0, -1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331493646930634, 4.858081206031886e-06, 0.3331493646930634, 0.3331493646930634, 0.00011968999597819392, 6.197030011742904e-05, 0.00010688013195754711, 7.604192781482615e-05, 0.00012529129261794686, 5.717419111781055e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([6], dtype=torch.int32)
[0.24991653945879322, 3.644355871847079e-06, 0.24991653945879322, 0.24991653945879322, 8.978708283074785e-05, 4.648786579208861e-05, 0.24991653945879322, 5.704388921997663e-05, 9.398897189626936e-05, 4.288999921606753e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24991653945879322, 3.644355871847079e-06, 0.24991653945879322, 0.24991653945879322, 8.978708283074785e-05, 4.648786579208861e-05, 0.24991653945879322, 5.704388921997663e-05, 9.398897189626936e-05, 4.288999921606753e-05]
[-1, 0, 0, -1, -1, -1, 0, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24991653945879322, 3.644355871847079e-06, 0.24991653945879322, 0.24991653945879322, 8.978708283074785e-05, 4.648786579208861e-05, 0.24991653945879322, 5.704388921997663e-05, 9.398897189626936e-05, 4.288999921606753e-05]
[-1, 0, 0, -1, -1, -1, 0, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  49
-----
It has processed 480 episodes
----target item:  742
[2.423940171925103e-05, 1.4533648323083764e-05, 0.00028741769626720274, 0.00010125568490875426, 0.9983740821584898, 0.00017249931480808583, 0.00029919084208663655, 0.00021344974796603527, 0.00035234317597704747, 0.0001609883294541585]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2131306489538567e-05, 7.273782755061548e-06, 0.4996650545321558, 5.067632285910223e-05, 0.4996650545321558, 8.633224868377436e-05, 0.0001497386712038152, 0.00010682707199964445, 0.00017634028705750823, 8.05712446399255e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2131306489538567e-05, 7.273782755061548e-06, 0.4996650545321558, 5.067632285910223e-05, 0.4996650545321558, 8.633224868377436e-05, 0.0001497386712038152, 0.00010682707199964445, 0.00017634028705750823, 8.05712446399255e-05]
[0, -1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[1.2131306489538567e-05, 7.273782755061548e-06, 0.4996650545321558, 5.067632285910223e-05, 0.4996650545321558, 8.633224868377436e-05, 0.0001497386712038152, 0.00010682707199964445, 0.00017634028705750823, 8.05712446399255e-05]
[0, -1, -1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 480.
Rec Success! in episode: 480.
total combined:  49
-----
It has processed 481 episodes
----target item:  1788
[2.6904247411054933e-05, 1.5119593588720712e-05, 0.9982193884976559, 0.0001060858198024307, 0.0003561318458434267, 0.00018473221781079786, 0.00031923558774622735, 0.00022824937513233793, 0.0003743539757438202, 0.0001697988392652054]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49956117659615984, 7.5666352005091425e-06, 0.49956117659615984, 5.3090891212232676e-05, 0.00017822699697374415, 9.244966101457062e-05, 0.0001597621802015785, 0.00011422792195016232, 0.0001873463035690899, 8.497621755839841e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331399246267467, 0.3331399246267467, 0.3331399246267467, 3.540446360808327e-05, 0.00011885336795553729, 6.165145440647336e-05, 0.00010653982567901515, 7.617461702695392e-05, 0.0001249347154543994, 5.666767562955669e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991116383515188, 0.24991116383515188, 0.24991116383515188, 2.655932252842023e-05, 8.91600835437997e-05, 4.624899504349156e-05, 0.24991116383515188, 5.7143817923451094e-05, 9.372212045015194e-05, 4.251031990321335e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 481.
Rec Success! in episode: 481.
total combined:  49
-----
It has processed 482 episodes
----target item:  1723
[2.44900053524381e-05, 1.4122762075324284e-05, 0.00027551660698072047, 9.372109296865567e-05, 0.0003187749955152043, 0.00016563676162914458, 0.00028885818812016904, 0.9983284245964931, 0.00033608645177119704, 0.0001543685390942019]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2256935366681812e-05, 7.068262316204096e-06, 0.49965064518788654, 4.690621183948528e-05, 0.00015954282003271029, 8.289908688945184e-05, 0.00014456983944975953, 0.49965064518788654, 0.00016820698312207107, 7.725948521029459e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331807515077774, 4.713311136587078e-06, 0.3331807515077774, 3.127834830511613e-05, 0.00010638752734158827, 5.527938437615717e-05, 9.6403133303504e-05, 0.3331807515077774, 0.00011216502887611277, 5.1518743328731796e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991504644687734, 0.24991504644687734, 0.24991504644687734, 2.346152901714742e-05, 7.980005962715655e-05, 4.146442989699427e-05, 7.231088059001308e-05, 0.24991504644687734, 8.413369702311486e-05, 3.8643616336234276e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 482.
Rec Success! in episode: 482.
total combined:  49
-----
It has processed 483 episodes
----target item:  1900
[0.9979620751333746, 1.541980645685215e-05, 0.000299672265510662, 0.00010707925267997512, 0.0003524176758972532, 0.0001816172929492796, 0.0003154158779779154, 0.00022730382476297226, 0.00037058186609610633, 0.00016841700429449184]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 483.
Rec Success! in episode: 483.
total combined:  49
-----
It has processed 484 episodes
----target item:  1559
[2.3082348547188324e-05, 0.9979661681789826, 0.00029988491565389737, 0.00010326019694232991, 0.0003511029265947718, 0.00017887073324838706, 0.00031593233202449763, 0.00022348932058356206, 0.00036999559464932216, 0.00016821345277334622]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 484.
Rec Success! in episode: 484.
total combined:  49
-----
It has processed 485 episodes
----target item:  950
[0.998073311827875, 1.4088629776593318e-05, 0.00028588352803992636, 9.820970696820728e-05, 0.000334756109528563, 0.00017127630272016745, 0.0002985332498526801, 0.00021300596029417073, 0.0003504655517959535, 0.0001604691331485924]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 485.
Rec Success! in episode: 485.
total combined:  49
-----
It has processed 486 episodes
----target item:  1480
[2.3753635852283313e-05, 0.9980122877835897, 0.000294070380869461, 0.00010294510334448633, 0.0003405331706436633, 0.0001757677981445523, 0.00030601911927219226, 0.00021805056628418736, 0.00035971050500691206, 0.00016686193699249176]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3753635852283313e-05, 0.9980122877835897, 0.000294070380869461, 0.00010294510334448633, 0.0003405331706436633, 0.0001757677981445523, 0.00030601911927219226, 0.00021805056628418736, 0.00035971050500691206, 0.00016686193699249176]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1889246095829962e-05, 0.4995283151560477, 0.00014718905136854618, 0.4995283151560477, 0.00017044475611031955, 8.797586276299975e-05, 0.00015316967228435897, 0.00010913936965311301, 0.00018004345708917473, 8.351827254015555e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.929435611022834e-06, 0.33315633127502314, 0.33315633127502314, 0.33315633127502314, 0.00011367673845083465, 5.867478336982729e-05, 0.00010215526233966043, 7.278961149567882e-05, 0.00012007851369779414, 5.570182996576197e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990190950636146, 0.24990190950636146, 0.24990190950636146, 0.24990190950636146, 8.526938058357878e-05, 4.401219195767758e-05, 7.662707482431188e-05, 5.459978153613456e-05, 9.007137804922226e-05, 4.17821676033271e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 486.
Rec Success! in episode: 486.
total combined:  49
-----
It has processed 487 episodes
----target item:  703
[2.2505987254889543e-05, 0.9980557785551772, 0.00028655726244515437, 9.949766403299784e-05, 0.00033568317575640404, 0.00017387947267549328, 0.00030036594302217107, 0.0002129246314524438, 0.0003511646666713181, 0.00016164264151201046]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 487.
Rec Success! in episode: 487.
total combined:  49
-----
It has processed 488 episodes
----target item:  710
[2.27983035454882e-05, 0.9980842044484343, 0.0002802877736391701, 9.808964263125233e-05, 0.0003307710877415074, 0.0001712174305156711, 0.0002949469015095341, 0.00021096994482795703, 0.00034727010919183824, 0.00015944435796344408]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 488.
Rec Success! in episode: 488.
total combined:  49
-----
It has processed 489 episodes
----target item:  447
[0.9980568109932033, 1.4195316962727387e-05, 0.00028814239547355806, 9.996325509019932e-05, 0.0003356843932400821, 0.00017344310657464886, 0.00030116757836166734, 0.00021536037166300118, 0.0003536798229882694, 0.00016155276644261332]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 489.
Rec Success! in episode: 489.
total combined:  49
-----
It has processed 490 episodes
----target item:  1937
[2.5004139015160653e-05, 1.4743768404249859e-05, 0.00028575260273936657, 9.949926229184767e-05, 0.000331885004036771, 0.00017204186874590684, 0.9983486374809752, 0.00021367970775041777, 0.0003496229433060581, 0.0001591332227348333]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 490.
Rec Success! in episode: 490.
total combined:  49
-----
It has processed 491 episodes
----target item:  1937
[2.276931709943038e-05, 0.998095399951925, 0.00028185139354552577, 9.83371449299599e-05, 0.0003271602670176389, 0.00016889286065716454, 0.0002946961454424901, 0.0002100745324575164, 0.00034432740585763993, 0.000156490981067583]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 491.
Rec Success! in episode: 491.
total combined:  49
-----
It has processed 492 episodes
----target item:  1680
[2.1977435309142373e-05, 0.998107950884892, 0.0002783493912607226, 9.726935680063729e-05, 0.0003276394456975605, 0.00016861899658155842, 0.00029048796280739585, 0.00020827457726251548, 0.00034228488905592934, 0.0001571470603327174]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 492.
Rec Success! in episode: 492.
total combined:  49
-----
It has processed 493 episodes
----target item:  984
[0.9979947121675821, 1.4463348117303645e-05, 0.0002978034510165214, 0.00010272148909900329, 0.00034629852198973224, 0.00017827154849850413, 0.0003123240748068058, 0.00022110204521646483, 0.00036618115491934003, 0.00016612219875431988]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 493.
Rec Success! in episode: 493.
total combined:  49
-----
It has processed 494 episodes
----target item:  1212
[0.9979755478733892, 1.4975897050941148e-05, 0.0002980126360718247, 0.00010333004651277119, 0.00035068395148401025, 0.00018192568962254526, 0.00031388742100784295, 0.0002253802107728421, 0.00036761408416273494, 0.00016864218992537267]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 494.
Rec Success! in episode: 494.
total combined:  49
-----
It has processed 495 episodes
----target item:  1549
[0.9980676878274422, 1.4549754403206863e-05, 0.00028669486283068135, 9.969745093268186e-05, 0.00033419571568504033, 0.00017167521562179623, 0.000301167923409171, 0.0002143349853778967, 0.0003496386925823244, 0.00016035757171498015]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 495.
Rec Success! in episode: 495.
total combined:  49
-----
It has processed 496 episodes
----target item:  1914
[2.3083987787256496e-05, 0.9980579333704224, 0.0002868949893604262, 0.0001000922238371606, 0.00033270899375785343, 0.00017324015556615383, 0.0002984061368925033, 0.00021279503145218845, 0.00035359132052822034, 0.00016125379039587896]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 496.
Rec Success! in episode: 496.
total combined:  49
-----
It has processed 497 episodes
----target item:  1914
[2.2686084372487654e-05, 0.998083799997137, 0.00028269925932837456, 9.8141492135701e-05, 0.00032853653393323117, 0.0001708866759277401, 0.00029468374590094914, 0.000210761663227583, 0.00034868237326861497, 0.00015912217476825847]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2686084372487654e-05, 0.998083799997137, 0.00028269925932837456, 9.8141492135701e-05, 0.00032853653393323117, 0.0001708866759277401, 0.00029468374590094914, 0.000210761663227583, 0.00034868237326861497, 0.00015912217476825847]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1354478084423582e-05, 0.49954502713695975, 0.0001414921364049756, 0.49954502713695975, 0.00016443387996040957, 8.552948075493524e-05, 0.00014749042098803012, 0.00010548707511008166, 0.00017451695500633255, 7.964129977155199e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.572663275346607e-06, 0.33316249793740477, 0.33316249793740477, 0.33316249793740477, 0.00010966619467143562, 5.7042336341366305e-05, 9.836606193407137e-05, 7.035269201899183e-05, 0.00011639091874374432, 5.3115320800896016e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990531229436688, 0.24990531229436688, 0.24990531229436688, 0.24990531229436688, 8.226065297616144e-05, 4.2787477479136174e-05, 7.378441925183215e-05, 5.277158017064338e-05, 8.730487097725079e-05, 3.984182167723244e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 497.
Rec Success! in episode: 497.
total combined:  49
-----
It has processed 498 episodes
----target item:  1914
[2.2532681112228067e-05, 0.9981059213063483, 0.00027977061686476764, 9.697011608588625e-05, 0.00032518880726198075, 0.00016892810598834017, 0.00029097894394389056, 0.0002080650011596808, 0.0003444686212792191, 0.00015717579995550238]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 498.
Rec Success! in episode: 498.
total combined:  49
-----
It has processed 499 episodes
----target item:  1914
[2.4753578020215843e-05, 1.4754375039982132e-05, 0.00027909094062123754, 9.649014354584462e-05, 0.9984180753054508, 0.00016930633345789322, 0.0002900724849941238, 0.00020755118320660296, 0.0003433997206562347, 0.00015650593500702008]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2388316435397778e-05, 7.384058444098806e-06, 0.49967398820499415, 4.82900060010175e-05, 0.49967398820499415, 8.473201052714184e-05, 0.00014517132555037573, 0.00010387224553980641, 0.00017185977719432513, 7.832585031955139e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 499.
Rec Success! in episode: 499.
total combined:  49
-----
It has processed 500 episodes
----target item:  1522
[2.255853230022789e-05, 0.9981220676349837, 0.0002759151196139513, 9.514948081475148e-05, 0.0003222188067437061, 0.0001663231814087626, 0.0002917333272551186, 0.00020745067629680523, 0.0003403940408151029, 0.0001561891997678366]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 500.
Rec Success! in episode: 500.
total combined:  49
-----
It has processed 501 episodes
----target item:  683
[0.9980532920962911, 1.4813769162142342e-05, 0.00028805547120170944, 9.954332776523817e-05, 0.00033853491019312257, 0.00017301632544068797, 0.000301193058639622, 0.00021714315572829242, 0.00035358717429956555, 0.0001608207112784132]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 501.
Rec Success! in episode: 501.
total combined:  49
-----
It has processed 502 episodes
----target item:  1616
[2.3603836206051838e-05, 0.9978833443486673, 0.0003124928491991425, 0.00010794201185125677, 0.00036487491636055173, 0.00018886688498467405, 0.00032712319632870293, 0.00023084562859182765, 0.0003856845000067017, 0.00017522182780341797]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3603836206051838e-05, 0.9978833443486673, 0.0003124928491991425, 0.00010794201185125677, 0.00036487491636055173, 0.00018886688498467405, 0.00032712319632870293, 0.00023084562859182765, 0.0003856845000067017, 0.00017522182780341797]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.2046445743441155e-05, 0.4994879392355735, 0.00015912136962549216, 0.4994879392355735, 0.00018613443065287641, 9.62203859188835e-05, 0.0001668500339440626, 0.00011762201022352281, 0.00019668653691137783, 8.944031583349378e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.034558930566892e-06, 0.3331410250264607, 0.3331410250264607, 0.3331410250264607, 0.00012414516978190857, 6.41756396411013e-05, 0.00011128315013750396, 7.844977620782259e-05, 0.0001311830564234264, 5.965356949571449e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([7], dtype=torch.int32)
[6.027143121213633e-06, 0.24990651692694987, 0.24990651692694987, 0.24990651692694987, 9.312778866258629e-05, 4.8141505757187546e-05, 8.347931462753204e-05, 0.24990651692694987, 9.840727574157551e-05, 4.4749264290549794e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.19994113048965312, 0.19994113048965312, 0.19994113048965312, 0.19994113048965312, 7.450816238874569e-05, 3.851627081569802e-05, 6.678876863386928e-05, 0.19994113048965312, 7.873208831096236e-05, 3.580226158507164e-05]
[-1, 1, 0, 0, 1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 502.
Rec Success! in episode: 502.
total combined:  49
-----
It has processed 503 episodes
----target item:  1893
[2.4893698415557464e-05, 1.4612325450141073e-05, 0.0002966676997162642, 0.00010323990903626516, 0.0003462775983484219, 0.00017929796010262105, 0.00031003806758186285, 0.9981969195846285, 0.0003639036663912582, 0.0001641494903290365]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2459930565638393e-05, 7.313841337351614e-06, 0.499623001019637, 5.167420592637886e-05, 0.00017332076414812374, 8.97431991078949e-05, 0.00015518195529999983, 0.499623001019637, 0.00018214306046957776, 8.21610038710242e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.309568506387387e-06, 4.877624744167853e-06, 0.3332002158815253, 3.44616971897559e-05, 0.0001155881853178252, 5.985003343645906e-05, 0.3332002158815253, 0.3332002158815253, 0.00012147180363179414, 5.479344259771604e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.233339079715971e-06, 3.6589010501135253e-06, 0.2499467842918201, 2.5851094877083275e-05, 0.2499467842918201, 4.48958994748067e-05, 0.2499467842918201, 0.2499467842918201, 9.112084942552946e-05, 4.1102748812285264e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 503.
Rec Success! in episode: 503.
total combined:  49
-----
It has processed 504 episodes
----target item:  1255
[2.4754370498958445e-05, 1.4535712497912392e-05, 0.00028878038436927034, 0.00010145911603518834, 0.9983601930513181, 0.00017334150504369012, 0.0003017808816341323, 0.0002155031195114821, 0.00035563132517219383, 0.0001640205339191042]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2389132011011187e-05, 7.274871361334718e-06, 0.4996619173479616, 5.0778523426129494e-05, 0.4996619173479616, 8.675440924922723e-05, 0.00015103608395624195, 0.00010785556419319206, 0.00017798729460700844, 8.208942527243102e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 504.
Rec Success! in episode: 504.
total combined:  49
-----
It has processed 505 episodes
----target item:  1285
[2.581970572293664e-05, 1.4897660764510483e-05, 0.0003055195510056594, 0.00010892379573545008, 0.00035710646284161686, 0.00018480852299626057, 0.9982267941531145, 0.00022689082040922202, 0.00037499814494417865, 0.00017424118246559217]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.292328484168061e-05, 7.4565804738614584e-06, 0.49963269666464405, 5.4518562427912744e-05, 0.00017873900607657102, 9.25004029666112e-05, 0.49963269666464405, 0.00011356344381207307, 0.00018769415477537293, 8.721123533773507e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[8.6186606635529e-06, 4.97286391207709e-06, 0.3332097622022568, 3.6358943967205746e-05, 0.3332097622022568, 6.168939199110372e-05, 0.3332097622022568, 7.573653277717514e-05, 0.00012517500375167355, 5.816199616686962e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 505.
Rec Success! in episode: 505.
total combined:  49
-----
It has processed 506 episodes
----target item:  2011
[0.9980217143594922, 1.4860328973350585e-05, 0.00029284586904973204, 0.00010402839425458178, 0.00034040354473316686, 0.00017708008356011435, 0.00030515071609731856, 0.00021943872783803905, 0.00035941947387957597, 0.0001650585021219318]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 506.
Rec Success! in episode: 506.
total combined:  49
-----
It has processed 507 episodes
----target item:  2011
[0.9980757689547395, 1.4641615913011088e-05, 0.00028460115257047795, 0.0001010426290852004, 0.0003309081581438447, 0.00017249264460144964, 0.00029699771629090714, 0.00021336962494986135, 0.00034945934149939033, 0.00016071816220646851]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 507.
Rec Success! in episode: 507.
total combined:  49
-----
It has processed 508 episodes
----target item:  2011
[2.524677983432717e-05, 1.4848056864054173e-05, 0.00029657225174823634, 0.00010538663968328953, 0.00034521539581919833, 0.00017980824161122633, 0.0003098228679818836, 0.00022271531047149266, 0.9983324900093872, 0.00016789444659914257]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2635798791175481e-05, 7.4313263000386345e-06, 0.4996569286551157, 5.274511771618356e-05, 0.00017277737239409968, 8.99924971384008e-05, 0.00015506371293344537, 0.00011146712053176811, 0.4996569286551157, 8.402974396354576e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318362963488835, 4.95539264573496e-06, 0.33318362963488835, 3.517175237317219e-05, 0.00011521223613968893, 6.00092285664589e-05, 0.00010340032877936706, 7.432903993483699e-05, 0.33318362963488835, 5.603311689567197e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991671114471178, 0.24991671114471178, 0.24991671114471178, 2.6381874427419304e-05, 8.641920124110425e-05, 4.50121425776385e-05, 7.755924301604821e-05, 5.57532470110088e-05, 0.24991671114471178, 4.2029712879648555e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 508.
Rec Success! in episode: 508.
total combined:  49
-----
It has processed 509 episodes
----target item:  2011
[2.282845734943483e-05, 0.9980434072973143, 0.0002879217310301327, 0.00010243224963012634, 0.00033513390059610197, 0.00017481853347415353, 0.00030039498928127506, 0.0002162321369155426, 0.00035394321115508713, 0.0001628874932535701]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 509.
Rec Success! in episode: 509.
total combined:  49
-----
It has processed 510 episodes
----target item:  841
[2.259539884392376e-05, 0.9980196790379258, 0.00029048307560746085, 0.00010045403631095514, 0.00034117700585226346, 0.00017564214525638886, 0.00030653056381666177, 0.0002190644596783977, 0.00036041615795801533, 0.0001639581187500587]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 510.
Rec Success! in episode: 510.
total combined:  49
-----
It has processed 511 episodes
----target item:  81
[2.306767273008677e-05, 0.9979992325945144, 0.000295988340462291, 0.00010346890731728457, 0.00034518861794201143, 0.00017834410555877625, 0.00030891887338355405, 0.00021945080770813472, 0.00036146197143038865, 0.00016487810895318542]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.306767273008677e-05, 0.9979992325945144, 0.000295988340462291, 0.00010346890731728457, 0.00034518861794201143, 0.00017834410555877625, 0.00030891887338355405, 0.00021945080770813472, 0.00036146197143038865, 0.00016487810895318542]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1545984104553309e-05, 0.4995251758043005, 0.0001481500415797632, 0.4995251758043005, 0.00017277608983211015, 8.926597112836108e-05, 0.0001546221174289052, 0.00010984096953242917, 0.00018092133633803597, 8.252588145484439e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.700520887119744e-06, 0.3331551485859243, 0.3331551485859243, 0.3331551485859243, 0.00011523191756537711, 5.9535373421472975e-05, 0.00010312424078276791, 7.325773814398282e-05, 0.00012066433807467657, 5.5040113351652935e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990120115331116, 0.24990120115331116, 0.24990120115331116, 0.24990120115331116, 8.64359885567253e-05, 4.465775598031866e-05, 7.735396480895264e-05, 5.4950964539076966e-05, 9.051087203430628e-05, 4.128584083594016e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 511.
Rec Success! in episode: 511.
total combined:  49
-----
It has processed 512 episodes
----target item:  698
[0.9979638278031959, 1.5113399475430803e-05, 0.00030218906369439076, 0.00010552387480202747, 0.0003520394781144924, 0.00018183477007204446, 0.00031615731486706766, 0.00022561162214961413, 0.0003691081473703184, 0.00016859452625900474]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 512.
Rec Success! in episode: 512.
total combined:  49
-----
It has processed 513 episodes
----target item:  1722
[0.9981700842870529, 1.3752808887853822e-05, 0.00026906435817161645, 9.446730246750943e-05, 0.00031664071750656363, 0.0001647359534082384, 0.00028398087072541893, 0.00020443862097629074, 0.0003317100554895634, 0.00015112502531390505]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 513.
Rec Success! in episode: 513.
total combined:  49
-----
It has processed 514 episodes
----target item:  1378
[0.9980223733835007, 1.4598814553898e-05, 0.00029340870528257387, 0.00010159476064804519, 0.0003424613998569441, 0.00017661045217217032, 0.00030566042347407067, 0.00021772796527751915, 0.00036069660321078273, 0.0001648674920234844]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 514.
Rec Success! in episode: 514.
total combined:  49
-----
It has processed 515 episodes
----target item:  936
[2.5179857572658367e-05, 1.4968116884901865e-05, 0.00031097844805124243, 0.00010832830645245651, 0.00036359299927002804, 0.9980588633886835, 0.00032679687780603285, 0.00023355269677836405, 0.0003836974612684247, 0.0001740418472322802]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 515.
Rec Success! in episode: 515.
total combined:  49
-----
It has processed 516 episodes
----target item:  12
[2.251157539503383e-05, 0.9980197419482482, 0.0002930722776075059, 0.00010058491318992544, 0.00034155194938006235, 0.0001774675455137405, 0.000304444948522863, 0.00021880528861819657, 0.0003570316847770648, 0.00016478786874752642]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2113]
random_location_list [2113]
Random Combined Rec Success! in episode: 516.
Random Combined Rec Success! in episode: 516.
Rec Success! in episode: 516.
total combined:  50
-----
It has processed 517 episodes
----target item:  928
[2.5107951084181296e-05, 1.43571356009277e-05, 0.00029450114745641244, 0.00010444731924914452, 0.9983244842836123, 0.0001778710515351123, 0.0003092279199268984, 0.00022134962061949736, 0.0003637668559912364, 0.00016488671492432793]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2566353506252823e-05, 7.185645722088914e-06, 0.4996544059447088, 5.227515108917511e-05, 0.4996544059447088, 8.902321438436156e-05, 0.00015476640617851335, 0.0001107839334182872, 0.0001820627613506877, 8.252464493326461e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 517.
Rec Success! in episode: 517.
total combined:  50
-----
It has processed 518 episodes
----target item:  904
[0.998082265904382, 1.4412817893960707e-05, 0.00028280978278956057, 9.949084733204612e-05, 0.00033219511313384997, 0.00017048281721142398, 0.00029811287360539696, 0.0002112231882757552, 0.0003489903984209886, 0.00016001625695496663]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 518.
Rec Success! in episode: 518.
total combined:  50
-----
It has processed 519 episodes
----target item:  1773
[2.6158376585740262e-05, 1.585799217379439e-05, 0.0002996395575480907, 0.00010370475842335912, 0.998297293245867, 0.00018101490989998407, 0.0003138831577081855, 0.0002249566369975756, 0.00036957797529030083, 0.00016791338950614148]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3092295948121708e-05, 7.936942340507963e-06, 0.4996488816706077, 5.190434444801239e-05, 0.4996488816706077, 9.0598159395147e-05, 0.00015709886201755778, 0.00011259104162725311, 0.00018497417882751613, 8.404083418024643e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 519.
Rec Success! in episode: 519.
total combined:  50
-----
It has processed 520 episodes
----target item:  1773
[2.521496496674904e-05, 1.5330933976858246e-05, 0.0002911686142688755, 0.00010128981382771325, 0.9983473569929225, 0.00017571395897648807, 0.00030364205322224114, 0.00021826804391569997, 0.0003587426982591296, 0.00016327192566341527]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.261974768948316e-05, 7.672924348187983e-06, 0.4996593002737543, 5.069417687893257e-05, 0.4996593002737543, 8.794245126763591e-05, 0.00015196872589886228, 0.00010924019313631825, 0.00017954585078522526, 8.171538248676791e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 520.
Rec Success! in episode: 520.
total combined:  50
-----
It has processed 521 episodes
----target item:  752
[2.3648574850221513e-05, 0.9980331745190414, 0.00029015626717672374, 0.00010057608953823874, 0.0003377078807573028, 0.000175755500052458, 0.00030313393238519013, 0.00021675580224891688, 0.00035570459756632784, 0.00016338683638313385]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3648574850221513e-05, 0.9980331745190414, 0.00029015626717672374, 0.00010057608953823874, 0.0003377078807573028, 0.000175755500052458, 0.00030313393238519013, 0.00021675580224891688, 0.00035570459756632784, 0.00016338683638313385]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1864936799713881e-05, 0.4995326820171661, 0.00014515433614480997, 0.4995326820171661, 0.0001686087497151291, 8.819373705802091e-05, 0.00015183139842171273, 0.00010872932039173762, 0.00017813365309117388, 8.211983404539842e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[7.913188939262687e-06, 0.33315782130704535, 0.33315782130704535, 0.33315782130704535, 0.00011245174886568674, 5.881984172192154e-05, 0.00010126227917644334, 7.251582288396135e-05, 0.00011880427828199858, 5.476891899481543e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[5.935995923673247e-06, 0.24991485536332292, 0.24991485536332292, 0.24991485536332292, 8.435450334879025e-05, 4.4123089107608795e-05, 7.59608396850988e-05, 0.24991485536332292, 8.911978685328786e-05, 4.1084331789947975e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[4.7494407598381145e-06, 0.19995899859329994, 0.19995899859329994, 0.19995899859329994, 0.19995899859329994, 3.530325838363595e-05, 6.077691305567613e-05, 0.19995899859329994, 7.130549845916465e-05, 3.287192284208056e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 521.
Rec Success! in episode: 521.
total combined:  50
-----
It has processed 522 episodes
----target item:  47
[0.9980495927839096, 1.5089230490305343e-05, 0.0002862168852890389, 0.00010010729628040335, 0.0003370578537916882, 0.00017488205594739598, 0.00030131934939693855, 0.00021590673279941336, 0.0003559165305129413, 0.0001639112815823111]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 522.
Rec Success! in episode: 522.
total combined:  50
-----
It has processed 523 episodes
----target item:  1181
[2.3238420401898078e-05, 0.9980524072013974, 0.0002868320222495124, 9.852831029857914e-05, 0.00033515296759630605, 0.0001724710800725379, 0.00030039606642123996, 0.00021602891585750642, 0.0003537268594773365, 0.00016121815622763188]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 523.
Rec Success! in episode: 523.
total combined:  50
-----
It has processed 524 episodes
----target item:  883
[0.9981144863837533, 1.4457009984809484e-05, 0.00027900414650762023, 9.639258147040382e-05, 0.00032551145539784135, 0.00016923270097382527, 0.0002918973633590277, 0.00020919193144069964, 0.0003428609484389551, 0.0001569654786736769]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 524.
Rec Success! in episode: 524.
total combined:  50
-----
It has processed 525 episodes
----target item:  1418
[0.9980467188966129, 1.454046939782167e-05, 0.0002893347395661482, 9.91373976232394e-05, 0.00033953450301441675, 0.00017518556097415345, 0.0003022523176287366, 0.00021441016252279497, 0.00035686011059947567, 0.00016202584206027022]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 525.
Rec Success! in episode: 525.
total combined:  50
-----
It has processed 526 episodes
----target item:  523
[2.2818173949602492e-05, 0.9979725502417649, 0.0002982172625529208, 0.00010362261397258667, 0.00034802639923818844, 0.0001820497532320363, 0.00031384927871169586, 0.000223659139951532, 0.0003671589724064623, 0.00016804816422000035]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 526.
Rec Success! in episode: 526.
total combined:  50
-----
It has processed 527 episodes
----target item:  1803
[2.639835438796421e-05, 1.557388912905877e-05, 0.9983455096627961, 9.830627291304045e-05, 0.0003301642603942305, 0.0001704078586281704, 0.00029611979322822726, 0.00021162565183361915, 0.00034667709516224206, 0.0001592171615273787]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49959263463637954, 7.793494562968825e-06, 0.49959263463637954, 4.919448168049296e-05, 0.0001652209892433316, 8.527559870885442e-05, 0.0001481844373866502, 0.00010590183051147238, 0.00017348435152344298, 7.967554362382622e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331539643038661, 0.3331539643038661, 0.3331539643038661, 3.2805400755475234e-05, 0.0001101778203609532, 5.686613812655222e-05, 9.88169747527051e-05, 7.06207662320969e-05, 0.00011568825368449857, 5.313173448936675e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991761591511627, 0.24991761591511627, 0.24991761591511627, 2.4609185014741193e-05, 8.265060945280741e-05, 4.265850384396193e-05, 0.24991761591511627, 5.297662769135354e-05, 8.678429689596082e-05, 3.985711663603759e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 527.
Rec Success! in episode: 527.
total combined:  50
-----
It has processed 528 episodes
----target item:  1686
[0.9981642637497924, 1.3671702143575288e-05, 0.0002719386048587845, 9.453991373882783e-05, 0.00031912831456687283, 0.00016384106852314716, 0.0002838277773245937, 0.00020465274037655647, 0.0003339297477658652, 0.000150206380909691]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 528.
Rec Success! in episode: 528.
total combined:  50
-----
It has processed 529 episodes
----target item:  47
[2.5766047783430923e-05, 1.5061215596437887e-05, 0.9982921943368439, 0.00010307422614797686, 0.00034157400485478653, 0.0001759114696132915, 0.00030630721552275483, 0.00021834374874556074, 0.0003592716626005579, 0.00016249607229134818]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4995791252879094, 7.5371408853290285e-06, 0.4995791252879094, 5.158182346897066e-05, 0.0001709351666120149, 8.80320397335149e-05, 0.00015328647430914338, 0.0001092665851032233, 0.00017979167217865462, 8.131852189023625e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33318028298298125, 5.026684675043806e-06, 0.33318028298298125, 3.440105014449001e-05, 0.00011400041415003557, 5.8710499348983494e-05, 0.33318028298298125, 7.287228369338958e-05, 0.00011990701208731489, 5.4233106956845826e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499148415851112, 0.2499148415851112, 0.2499148415851112, 2.5803846855069868e-05, 8.551044854115359e-05, 4.403809557041963e-05, 0.2499148415851112, 5.466069322027977e-05, 8.994092226122515e-05, 4.067965310684617e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 529.
Rec Success! in episode: 529.
total combined:  50
-----
It has processed 530 episodes
----target item:  1184
[2.3401961289172492e-05, 0.9979912271286012, 0.000296598463636947, 0.0001030435930036974, 0.0003457493716775856, 0.00017851501125843529, 0.0003095983168274349, 0.00022249634728019143, 0.00036327652298968823, 0.00016609328343548672]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 530.
Rec Success! in episode: 530.
total combined:  50
-----
It has processed 531 episodes
----target item:  1262
[0.9979810533986309, 1.490950340689142e-05, 0.0002995732720054056, 0.00010545800648099884, 0.00034815369017234297, 0.00018154754368232835, 0.00031141914669333007, 0.00022398862399852242, 0.00036450867921493407, 0.00016938813571428502]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 531.
Rec Success! in episode: 531.
total combined:  50
-----
It has processed 532 episodes
----target item:  1115
[2.524029016886501e-05, 1.4970816777470452e-05, 0.00029729412192931325, 0.00010340266712388972, 0.0003480876663555599, 0.00018105196312949413, 0.00030988463897494345, 0.9981875429235195, 0.0003644627120152368, 0.00016806220000584754]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2633471825594563e-05, 7.493312901672405e-06, 0.49962080926230545, 5.175592962922488e-05, 0.00017422762164456023, 9.062157605408799e-05, 0.00015510593695565802, 0.49962080926230545, 0.00018242379041283932, 8.411983596529266e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.425315629145397e-06, 4.997321969455228e-06, 0.33319922433324184, 3.451624769706055e-05, 0.00011619313550031682, 6.0435911173638344e-05, 0.33319922433324184, 0.33319922433324184, 0.0001216591950107828, 5.6099873294027966e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.320173186493464e-06, 3.7486952069033983e-06, 0.24994633982691286, 2.5892046398676732e-05, 0.24994633982691286, 4.533544404907637e-05, 0.24994633982691286, 0.24994633982691286, 9.126152847469304e-05, 4.208280503249947e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 532.
Rec Success! in episode: 532.
total combined:  50
-----
It has processed 533 episodes
----target item:  465
[2.3150568617741007e-05, 0.9980300364260838, 0.00029119621133292156, 0.00010186979382297621, 0.00033990497728065877, 0.00017324538872757098, 0.0003030891694557309, 0.00021680154114033087, 0.00035567136282908113, 0.0001650345607092938]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2181]
random_location_list [2181]
Random Combined Rec Success! in episode: 533.
Random Combined Rec Success! in episode: 533.
Rec Success! in episode: 533.
total combined:  51
-----
It has processed 534 episodes
----target item:  1664
[2.441487693507176e-05, 1.4587333225521698e-05, 0.9983749259119297, 9.709550317613253e-05, 0.0003243491628754432, 0.000166686740366968, 0.00029056492835535786, 0.00020842545842571371, 0.0003420897182997011, 0.00015686036641040577]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49959950489108496, 7.299686989329297e-06, 0.49959950489108496, 4.8587824127932605e-05, 0.00016230844443173033, 8.341216390543864e-05, 0.00014540238399161882, 0.00010429874903065186, 0.00017118604389503448, 7.849492145858036e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33318759410891774, 4.868229695810089e-06, 0.33318759410891774, 3.240367547542373e-05, 0.00010824502341242051, 5.562835418968354e-05, 0.33318759410891774, 6.95578136444883e-05, 0.00011416557773179634, 5.234899909729582e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991892532149593, 0.24991892532149593, 0.24991892532149593, 2.4305502048906156e-05, 8.119293875566372e-05, 4.172597882484348e-05, 0.24991892532149593, 5.2174253606995646e-05, 8.56338561216394e-05, 3.926618465804987e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 534.
Rec Success! in episode: 534.
total combined:  51
-----
It has processed 535 episodes
----target item:  1272
[0.9980957078815841, 1.4282760401053882e-05, 0.00028136799090654896, 9.815447967710447e-05, 0.0003288334355860798, 0.0001703229981841658, 0.0002961903546457078, 0.00021125585334736096, 0.00034679385838125727, 0.00015709038728674036]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 535.
Rec Success! in episode: 535.
total combined:  51
-----
It has processed 536 episodes
----target item:  436
[2.45727600186357e-05, 1.4233997682798171e-05, 0.0002821951746033755, 9.906382687757522e-05, 0.9984005955319876, 0.000170778574593035, 0.00029448584041672854, 0.000209428751107146, 0.0003462365262797083, 0.0001584090164335166]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2297949918403537e-05, 7.123700817855574e-06, 0.49967038757733934, 4.957855693629398e-05, 0.49967038757733934, 8.546969717234448e-05, 0.00014738157676945306, 0.00010481298358980502, 0.00017328128614289338, 7.927909397420267e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 536.
Rec Success! in episode: 536.
total combined:  51
-----
It has processed 537 episodes
----target item:  1069
[2.525053971051294e-05, 1.449105670091441e-05, 0.00029761053214312234, 0.00010451366841993886, 0.00035149662523596264, 0.00017944530947708892, 0.00031107075290143297, 0.0002216028739861101, 0.9983251629686691, 0.00016935567275589707]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2637733488570149e-05, 7.252681117056199e-06, 0.49965535347660534, 5.230842201975043e-05, 0.00017592181089160882, 8.981122870816345e-05, 0.00015568892056673232, 0.0001109108198812739, 0.49965535347660534, 8.476143011610305e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[8.42808058696169e-06, 4.83679933441933e-06, 0.33321921123089865, 3.488438781827306e-05, 0.33321921123089865, 5.9894938744438554e-05, 0.0001038286469816952, 7.396621623416826e-05, 0.33321921123089865, 5.652723760401626e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 537.
Rec Success! in episode: 537.
total combined:  51
-----
It has processed 538 episodes
----target item:  1515
[2.552414112575714e-05, 1.445572039494361e-05, 0.0002932793305958998, 0.00010305352941138119, 0.9983268795766667, 0.00017812683941311621, 0.0003085755902747686, 0.00022109003020337624, 0.0003622877088346732, 0.00016672753307935096]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2774630578091218e-05, 7.234973622647435e-06, 0.4996547002281225, 5.157747567342686e-05, 0.4996547002281225, 8.915107303059306e-05, 0.00015443964017260048, 0.00011065380991398122, 0.00018132213031355184, 8.344581045024337e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 538.
Rec Success! in episode: 538.
total combined:  51
-----
It has processed 539 episodes
----target item:  122
[2.4824941911128814e-05, 1.4539820354044292e-05, 0.9983939449876497, 9.560618182114842e-05, 0.00032135203894208486, 0.0001644894052444705, 0.00028647551566604595, 0.00020457340077497364, 0.0003380796348984864, 0.00015611407273800947]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49960436986976586, 7.275843190426955e-06, 0.49960436986976586, 4.784210327417399e-05, 0.0001608071480481693, 8.231182297327817e-05, 0.00014335465494957664, 0.00010237017712237837, 0.0001691777717675844, 7.812073914274474e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.33315906776551274, 0.33315906776551274, 0.33315906776551274, 3.1903304870852294e-05, 0.00010723356872904123, 5.4889292131303274e-05, 9.55954472842131e-05, 6.826512103161237e-05, 0.00011281548386661935, 5.2094485548103026e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24992082230424698, 0.24992082230424698, 0.24992082230424698, 2.3648748344914615e-05, 7.935362145425283e-05, 4.078371680007721e-05, 0.24992082230424698, 5.064594442235196e-05, 8.369349463771719e-05, 3.8585257352743815e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2143]
random_location_list [2143]
Random Combined Rec Success! in episode: 539.
Random Combined Rec Success! in episode: 539.
Rec Success! in episode: 539.
total combined:  52
-----
It has processed 540 episodes
----target item:  1934
[0.9980931583202077, 1.4882445769417614e-05, 0.0002816316977170567, 0.00010018328638201458, 0.00033208851359078104, 0.00016913045888967992, 0.0002926265025961638, 0.00021051307014690452, 0.0003471281345509027, 0.00015865757014939415]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 540.
Rec Success! in episode: 540.
total combined:  52
-----
It has processed 541 episodes
----target item:  736
[0.9980250359398679, 1.497615358937113e-05, 0.0002925128194907757, 0.00010056928669335577, 0.00034242198474878553, 0.0001764209458868031, 0.0003050771928689895, 0.00021923914698460272, 0.0003578011571747437, 0.00016594537269462595]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 541.
Rec Success! in episode: 541.
total combined:  52
-----
It has processed 542 episodes
----target item:  1512
[2.3026627223759485e-05, 0.9980026182538303, 0.0002932633408729262, 0.00010264115771055022, 0.00034626303141788655, 0.0001770723443710913, 0.0003076418037569157, 0.00022150238423581875, 0.0003607580452711862, 0.0001652130113096554]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 542.
Rec Success! in episode: 542.
total combined:  52
-----
It has processed 543 episodes
----target item:  843
[2.268205936526008e-05, 0.9981083764757602, 0.00028000024346349186, 9.84964815065535e-05, 0.00032596804672135204, 0.000167680197985656, 0.0002894449727775467, 0.0002070405797938572, 0.00034226776535809574, 0.00015804317726807944]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 543.
Rec Success! in episode: 543.
total combined:  52
-----
It has processed 544 episodes
----target item:  1862
[0.9981564550716199, 1.4293667310096768e-05, 0.00027239149340404557, 9.444710345705373e-05, 0.00031821053701253164, 0.0001651682130078014, 0.00028719354514618057, 0.00020330678895266011, 0.00033520509648403743, 0.00015332848360572482]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 544.
Rec Success! in episode: 544.
total combined:  52
-----
It has processed 545 episodes
----target item:  1118
[0.9980586368478547, 1.4738732669772678e-05, 0.0002886337368750555, 0.00010115714624299976, 0.0003364262870096664, 0.00017291359846112478, 0.0003000349977695412, 0.00021317052599721534, 0.0003534720208009894, 0.00016081610631883905]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 545.
Rec Success! in episode: 545.
total combined:  52
-----
It has processed 546 episodes
----target item:  116
[2.6929359695600652e-05, 1.5494058671680837e-05, 0.9981516088812721, 0.00011098890268145346, 0.0003698566396214685, 0.00019178672016341376, 0.0003308731961627273, 0.00023556049532914673, 0.00038816445535330116, 0.0001787372910493156]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49954420718143844, 7.754300234853547e-06, 0.49954420718143844, 5.554653511813296e-05, 0.00018510188248614467, 9.598335986187528e-05, 0.00016559186699097788, 0.00011789078917014745, 0.00019426438166323114, 8.945252159745693e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331324198365542, 0.3331324198365542, 0.3331324198365542, 3.7042470699132424e-05, 0.00012343940164341496, 6.40086872696247e-05, 0.00011042870393234543, 7.86181549262324e-05, 0.0001295496226783766, 5.965344918796952e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.2499068981344731, 0.2499068981344731, 0.2499068981344731, 2.7968560960093532e-05, 9.341471636107212e-05, 4.8459449847645745e-05, 0.2499068981344731, 5.957244451913235e-05, 9.797217437029406e-05, 4.5020116049351646e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2142]
random_location_list [2142]
Random Combined Rec Success! in episode: 546.
Random Combined Rec Success! in episode: 546.
Rec Success! in episode: 546.
total combined:  53
-----
It has processed 547 episodes
----target item:  1111
[2.3600611098354575e-05, 0.9980927612458659, 0.0002792243432876888, 9.859181903248882e-05, 0.00032848552707809124, 0.00016867265792479754, 0.0002941781009046061, 0.00021157344853442816, 0.0003456469909876355, 0.00015726525528597407]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 547.
Rec Success! in episode: 547.
total combined:  53
-----
It has processed 548 episodes
----target item:  1943
[0.9981985858630993, 1.3780932411758285e-05, 0.0002660234959607063, 9.130128395213364e-05, 0.00031111655330132024, 0.00016082672949879086, 0.0002800402645096774, 0.00019891764467872626, 0.00032859131690561155, 0.00015081591568188513]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 548.
Rec Success! in episode: 548.
total combined:  53
-----
It has processed 549 episodes
----target item:  1055
[2.656150972040186e-05, 1.549496187350763e-05, 0.0003083305211245152, 0.0001092310472073376, 0.00036299199984138276, 0.00018697064248421119, 0.0003238902778036035, 0.00023266359801440333, 0.9982598444580183, 0.0001740209839124473]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.329437152759695e-05, 7.7554243761278e-06, 0.49964167673467813, 5.46715205275936e-05, 0.00018168208653177958, 9.358117110449395e-05, 0.0001621111801484056, 0.00011645107320745126, 0.49964167673467813, 8.709970322029738e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.3331769941212574, 5.171564147049962e-06, 0.3331769941212574, 3.6456712323249645e-05, 0.00012115140568724137, 6.240290741698719e-05, 0.00010810090156665807, 7.765328702564622e-05, 0.3331769941212574, 5.80808580610108e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 549.
Rec Success! in episode: 549.
total combined:  53
-----
It has processed 550 episodes
----target item:  1963
[0.9981474290283425, 1.3962865765778006e-05, 0.0002743104692684672, 9.459725593574912e-05, 0.000321159089733358, 0.00016703992394538346, 0.0002861300335549521, 0.0002053416519379911, 0.0003361422780228992, 0.00015388740349275663]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 550.
Rec Success! in episode: 550.
total combined:  53
-----
It has processed 551 episodes
----target item:  1963
[2.2769973843078147e-05, 0.9980670591305135, 0.00028470497488165245, 9.812112213379894e-05, 0.00033405436224253796, 0.00017356143240150693, 0.00029757158050633875, 0.0002133489710931401, 0.000349434481376161, 0.0001593739710086594]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 551.
Rec Success! in episode: 551.
total combined:  53
-----
It has processed 552 episodes
----target item:  1963
[0.9980270395116302, 1.4749859234898212e-05, 0.00029200803196231296, 0.00010078818337081956, 0.0003423008970890047, 0.00017739495685224426, 0.0003050189573362956, 0.00021848864982585992, 0.0003581925456083236, 0.00016401840709007821]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 552.
Rec Success! in episode: 552.
total combined:  53
-----
It has processed 553 episodes
----target item:  1963
[2.4094652908552256e-05, 1.408582555919932e-05, 0.00027909515382622935, 9.652395467828868e-05, 0.0003271179102533749, 0.00017035922765805013, 0.00029215891580935976, 0.00020962783039382875, 0.9984301305775224, 0.00015680595139066188]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2058474300188787e-05, 7.049429852639995e-06, 0.49967700783229896, 4.8306635968497416e-05, 0.00016371030240164576, 8.525843374093412e-05, 0.00014621463074106867, 0.0001049109034690055, 0.49967700783229896, 7.847552492818047e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331924294464633, 4.7006698767333545e-06, 0.3331924294464633, 3.221161899474767e-05, 0.00010916458537737351, 5.685165461620809e-05, 9.7498198383354e-05, 6.995622823212445e-05, 0.3331924294464633, 5.23287051296195e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 553.
Rec Success! in episode: 553.
total combined:  53
-----
It has processed 554 episodes
----target item:  1383
[2.3331606787027075e-05, 0.9979685488989974, 0.0002977662487729856, 0.00010589245828138208, 0.00035088187349874674, 0.00018133078820339155, 0.0003120037172418175, 0.0002219313300540494, 0.0003694906970801124, 0.00016882238108334647]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 554.
Rec Success! in episode: 554.
total combined:  53
-----
It has processed 555 episodes
----target item:  1077
[0.9979744113950302, 1.499083255213825e-05, 0.00029780802555286765, 0.00010436595500902368, 0.00034790269632034343, 0.00018203725781457068, 0.00031413062807653943, 0.00022627929645175235, 0.0003693501062425318, 0.00016872380694997013]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 555.
Rec Success! in episode: 555.
total combined:  53
-----
It has processed 556 episodes
----target item:  1572
[2.2600654178066264e-05, 0.9979556852501684, 0.00030002778733696816, 0.00010457378398756529, 0.00035368412280815383, 0.00018256512196254286, 0.00031605132359956346, 0.0002239669413515757, 0.0003710488023342179, 0.00016979621227289956]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 556.
Rec Success! in episode: 556.
total combined:  53
-----
It has processed 557 episodes
----target item:  606
[2.352432044112673e-05, 0.9979157416029649, 0.00030751311133599894, 0.00010798095982232385, 0.0003584617357202589, 0.00018645245621465176, 0.00032312039110970347, 0.00022895546011417523, 0.0003759951204338924, 0.00017225484184273086]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 557.
Rec Success! in episode: 557.
total combined:  53
-----
It has processed 558 episodes
----target item:  1570
[2.2270508933040176e-05, 0.9980123111826429, 0.0002928941252486517, 0.00010331123463205458, 0.00034197727167177837, 0.0001761256302694733, 0.00030730473473927685, 0.0002185158280229828, 0.00036024470603920005, 0.00016504477780048156]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 558.
Rec Success! in episode: 558.
total combined:  53
-----
It has processed 559 episodes
----target item:  1424
[2.4074601020255754e-05, 1.410758825042735e-05, 0.9983796764799985, 9.623451282093933e-05, 0.00032453623537366126, 0.000165858569151362, 0.00029100611296321854, 0.0002065195669099238, 0.0003421572061923854, 0.00015582912731964228]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4996006093916715, 7.059598520484798e-06, 0.4996006093916715, 4.815685092805986e-05, 0.00016240164416608934, 8.299752506281234e-05, 0.00014562278740059894, 0.00010334475341412768, 0.00017121937950916632, 7.79786776553292e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.3331573475096534, 0.3331573475096534, 0.3331573475096534, 3.211326891523537e-05, 0.00010829710769860972, 5.5346680488363495e-05, 9.710817135795608e-05, 6.891517600111224e-05, 0.00011417719123477408, 5.199987534361249e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991919920665104, 0.24991919920665104, 0.24991919920665104, 2.4089885788789075e-05, 8.123947028257796e-05, 4.151851420895764e-05, 0.24991919920665104, 5.169697060000856e-05, 8.565043639096862e-05, 3.900789612435233e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 559.
Rec Success! in episode: 559.
total combined:  53
-----
It has processed 560 episodes
----target item:  886
[2.397313596826709e-05, 1.4420251713467243e-05, 0.0002826121329995627, 9.836120834404621e-05, 0.99839347929704, 0.00017019563925606705, 0.0002973588844814053, 0.00021049809192293808, 0.000348155318205459, 0.00016094604006879298]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.199790079831389e-05, 7.216942738484879e-06, 0.49966870993203727, 4.922710243984225e-05, 0.49966870993203727, 8.517827616724252e-05, 0.0001488200126269534, 0.00010534855466839153, 0.00017424224247356357, 8.05491040130456e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 560.
Rec Success! in episode: 560.
total combined:  53
-----
It has processed 561 episodes
----target item:  1452
[2.2636187357968656e-05, 0.9980495756016781, 0.00028630991340553036, 9.908211582781878e-05, 0.00033567847878257224, 0.00017307597180610254, 0.00030292921563174473, 0.00021675884758548167, 0.00035272101201227785, 0.00016123265591254496]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 561.
Rec Success! in episode: 561.
total combined:  53
-----
It has processed 562 episodes
----target item:  594
[2.3590258275766147e-05, 0.9979749963492094, 0.00029827436389186685, 0.00010371366425346018, 0.000349326109713165, 0.00017955717632241349, 0.0003125956505450388, 0.00022284484648484195, 0.00036667301494521486, 0.00016842856635876724]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2191]
random_location_list [2191]
Random Combined Rec Success! in episode: 562.
Random Combined Rec Success! in episode: 562.
Rec Success! in episode: 562.
total combined:  54
-----
It has processed 563 episodes
----target item:  12
[2.221900861142499e-05, 0.998038540638278, 0.0002882845415594534, 0.00010020101456303957, 0.00033639764867437935, 0.00017469446323352115, 0.00030330046903726926, 0.00021721509800486108, 0.00035677350924905857, 0.00016237360878894045]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2113]
random_location_list [2113]
Random Combined Rec Success! in episode: 563.
Random Combined Rec Success! in episode: 563.
Rec Success! in episode: 563.
total combined:  55
-----
It has processed 564 episodes
----target item:  1176
[2.5289350094714335e-05, 1.5135371591904723e-05, 0.0002927504013444473, 0.00010285214684431707, 0.00034431236695471997, 0.000175425131201007, 0.00030651159701768066, 0.00021999629994472598, 0.9983515256803515, 0.0001662016546548494]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2656960049227261e-05, 7.575038221681561e-06, 0.4996607397302128, 5.1476036699648596e-05, 0.00017232344274088762, 8.779778321411533e-05, 0.00015340469500196746, 0.00011010501926501435, 0.4996607397302128, 8.31815643819793e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.33318532892546027, 5.051210553137827e-06, 0.33318532892546027, 3.4325410935451995e-05, 0.00011490925419153685, 5.85455909441997e-05, 0.00010229379596751586, 7.342057148609648e-05, 0.33318532892546027, 5.546738954136863e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 564.
Rec Success! in episode: 564.
total combined:  55
-----
It has processed 565 episodes
----target item:  1107
[2.339035674149782e-05, 0.9979702809222983, 0.00029900204071913676, 0.00010424111721871517, 0.0003514002282836718, 0.0001815702340396347, 0.0003119404922516466, 0.00022273491464529517, 0.0003658628756285775, 0.00016957681817340072]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 565.
Rec Success! in episode: 565.
total combined:  55
-----
It has processed 566 episodes
----target item:  1562
[2.2732842257339555e-05, 0.9979523475325514, 0.00030294734531070795, 0.00010506668430804346, 0.0003548932849408334, 0.00018156887469035504, 0.0003148028043604973, 0.00022323063390887674, 0.0003721613746353134, 0.00017024862303694516]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 566.
Rec Success! in episode: 566.
total combined:  55
-----
It has processed 567 episodes
----target item:  1906
[2.2163481777863373e-05, 0.9980843673616093, 0.0002828963436646029, 0.00010048441158300465, 0.00033021428379161516, 0.00017019210121904137, 0.00029352271394566273, 0.00021001236636111103, 0.00034602087972550696, 0.000160126056322474]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 567.
Rec Success! in episode: 567.
total combined:  55
-----
It has processed 568 episodes
----target item:  1906
[2.4825280966031826e-05, 1.45537781978468e-05, 0.9982616094068435, 0.00010635916987980982, 0.0003480427191743075, 0.00017878414832366973, 0.0003099225113727705, 0.00022178904376904512, 0.00036531950584605224, 0.00016879443562691908]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 568.
Rec Success! in episode: 568.
total combined:  55
-----
It has processed 569 episodes
----target item:  1842
[2.2868800037895783e-05, 0.9980860152193881, 0.00028314635834393657, 9.888707571317643e-05, 0.0003323852894594233, 0.00017006468486765357, 0.0002928087135038949, 0.00021013571918210224, 0.0003463996070222558, 0.00015728853248178236]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 569.
Rec Success! in episode: 569.
total combined:  55
-----
It has processed 570 episodes
----target item:  1553
[0.9980547366353347, 1.4354993367512407e-05, 0.0002895062157802971, 9.97123245604598e-05, 0.0003382653010886246, 0.00017453370762483177, 0.00029914833432302863, 0.00021463152404376974, 0.0003535577173599072, 0.0001615532465168968]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9980547366353347, 1.4354993367512407e-05, 0.0002895062157802971, 9.97123245604598e-05, 0.0003382653010886246, 0.00017453370762483177, 0.00029914833432302863, 0.00021463152404376974, 0.0003535577173599072, 0.0001615532465168968]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995381399937316, 7.184843098489862e-06, 0.00014490126767501528, 0.4995381399937316, 0.00016930576362964657, 8.73561744389316e-05, 0.00014972726146637088, 0.00010742560339555705, 0.00017695979792231435, 8.085930091075357e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.33316019246435896, 4.791833731752977e-06, 0.33316019246435896, 0.33316019246435896, 0.00011291618453174792, 5.826101664507493e-05, 9.985856785214334e-05, 7.164605029620519e-05, 0.00011802093897173122, 5.39280148945148e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.33316019246435896, 4.791833731752977e-06, 0.33316019246435896, 0.33316019246435896, 0.00011291618453174792, 5.826101664507493e-05, 9.985856785214334e-05, 7.164605029620519e-05, 0.00011802093897173122, 5.39280148945148e-05]
[-1, 0, 0, -1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.33316019246435896, 4.791833731752977e-06, 0.33316019246435896, 0.33316019246435896, 0.00011291618453174792, 5.826101664507493e-05, 9.985856785214334e-05, 7.164605029620519e-05, 0.00011802093897173122, 5.39280148945148e-05]
[-1, 0, 0, -1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.33316019246435896, 4.791833731752977e-06, 0.33316019246435896, 0.33316019246435896, 0.00011291618453174792, 5.826101664507493e-05, 9.985856785214334e-05, 7.164605029620519e-05, 0.00011802093897173122, 5.39280148945148e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([6], dtype=torch.int32)
[0.24992131563208306, 3.5946112939588774e-06, 0.24992131563208306, 0.24992131563208306, 8.470448160564219e-05, 4.3704711004924445e-05, 0.24992131563208306, 5.3745542099197645e-05, 8.853383149340175e-05, 4.045429417053042e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24992131563208306, 3.5946112939588774e-06, 0.24992131563208306, 0.24992131563208306, 8.470448160564219e-05, 4.3704711004924445e-05, 0.24992131563208306, 5.3745542099197645e-05, 8.853383149340175e-05, 4.045429417053042e-05]
[-1, 0, 0, -1, -1, -1, 0, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24992131563208306, 3.5946112939588774e-06, 0.24992131563208306, 0.24992131563208306, 8.470448160564219e-05, 4.3704711004924445e-05, 0.24992131563208306, 5.3745542099197645e-05, 8.853383149340175e-05, 4.045429417053042e-05]
[-1, 0, 0, -1, -1, -1, 0, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  55
-----
It has processed 571 episodes
----target item:  471
[2.296046274939887e-05, 0.9979937069004156, 0.0002960274913980618, 0.00010372924610584701, 0.0003447664362618682, 0.00017780608018467124, 0.000310539779451748, 0.000222506431337161, 0.0003619360409332016, 0.00016602113116257446]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 571.
Rec Success! in episode: 571.
total combined:  55
-----
It has processed 572 episodes
----target item:  1684
[2.2565363718986504e-05, 0.9980292774163454, 0.00029047904357730524, 0.00010218884637790312, 0.00033980589527662767, 0.00017738362035878147, 0.00030148483823655805, 0.00021685955812289476, 0.0003569987646257832, 0.0001629566533596805]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 572.
Rec Success! in episode: 572.
total combined:  55
-----
It has processed 573 episodes
----target item:  499
[2.4110922504523184e-05, 1.4234834820191328e-05, 0.00027854379155895957, 9.589222954765397e-05, 0.00032626368654384383, 0.000167835291459414, 0.00028940612298025703, 0.00020658478727669704, 0.9984429150492945, 0.00015421328401386404]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2506040280052285e-05, 7.370059164282543e-06, 0.49966974484909055, 4.942000868613413e-05, 0.0001683566555814992, 8.681414227843635e-05, 0.00014954983551095734, 0.00010679369710387634, 0.49966974484909055, 7.969986321372405e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.340027911354027e-06, 4.914944919575291e-06, 0.33321975023121686, 3.295721448132054e-05, 0.0001122736833697492, 5.7894613601819594e-05, 0.33321975023121686, 7.121857875539263e-05, 0.33321975023121686, 5.3150243310329205e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.24993766756046826, 3.6865457960833056e-06, 0.24993766756046826, 2.472017133148807e-05, 8.421296315835479e-05, 4.342493107900349e-05, 0.24993766756046826, 5.341881880873814e-05, 0.24993766756046826, 3.9866327953362e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2183]
random_location_list [2183]
Random Combined Rec Success! in episode: 573.
Random Combined Rec Success! in episode: 573.
Rec Success! in episode: 573.
total combined:  56
-----
It has processed 574 episodes
----target item:  1951
[0.9981449736228198, 1.4430769328313315e-05, 0.00027218046407759294, 9.426476751041983e-05, 0.00031977956016549056, 0.00016697814234364227, 0.00028884264034018304, 0.00020589314304673048, 0.0003384477815000761, 0.00015420910886780712]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 574.
Rec Success! in episode: 574.
total combined:  56
-----
It has processed 575 episodes
----target item:  794
[2.2762648358431298e-05, 0.9980323863942835, 0.00029102489351616646, 0.00010132976603020683, 0.0003401471263647029, 0.00017644008463827763, 0.0003017013460138776, 0.00021645720166312932, 0.00035588643639503965, 0.00016186410273624785]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 575.
Rec Success! in episode: 575.
total combined:  56
-----
It has processed 576 episodes
----target item:  92
[2.4759271208846e-05, 1.4363618705085436e-05, 0.0002823187067685001, 9.74241464486713e-05, 0.00032778079743475826, 0.00016716714406938286, 0.00029639200526953663, 0.00020988453508713457, 0.9984231960762281, 0.0001567136987800682]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2391153941778836e-05, 7.188491496152691e-06, 0.49967607759000765, 4.87573962136892e-05, 0.00016404288663884387, 8.366134038029261e-05, 0.00014833388807887005, 0.00010503990857914197, 0.49967607759000765, 7.84297546559284e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[8.263457481506665e-06, 4.793887164483283e-06, 0.3332257868066079, 3.2515508435605395e-05, 0.3332257868066079, 5.579237674930855e-05, 9.89214388720883e-05, 7.00493935014805e-05, 0.3332257868066079, 5.2303517971726875e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 576.
Rec Success! in episode: 576.
total combined:  56
-----
It has processed 577 episodes
----target item:  1086
[2.267772376067092e-05, 0.9980385699714921, 0.000290551664984004, 9.916580175549362e-05, 0.00033771348645551585, 0.00017600284499841106, 0.00030246090546000233, 0.00021596263943030237, 0.00035576781669727784, 0.00016112714496617413]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.267772376067092e-05, 0.9980385699714921, 0.000290551664984004, 9.916580175549362e-05, 0.00033771348645551585, 0.00017600284499841106, 0.00030246090546000233, 0.00021596263943030237, 0.00035576781669727784, 0.00016112714496617413]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1350556334862855e-05, 0.49953395377685994, 0.00014542566425068614, 0.49953395377685994, 0.00016903089540688853, 8.809218369240323e-05, 0.0001513864258489326, 0.00010809268738560558, 0.00017806737078951637, 8.064666257139671e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.570123501712152e-06, 0.33315844720091337, 0.33315844720091337, 0.33315844720091337, 0.00011273321906741553, 5.875207262209171e-05, 0.0001009654422523119, 7.20911794100958e-05, 0.00011875999279096984, 5.378636761541227e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990303267944963, 0.24990303267944963, 0.24990303267944963, 0.24990303267944963, 8.456148587964323e-05, 4.4070085113614775e-05, 7.573444535674201e-05, 5.407578440644097e-05, 8.90821847946576e-05, 4.034529665038736e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 577.
Rec Success! in episode: 577.
total combined:  56
-----
It has processed 578 episodes
----target item:  1779
[2.4219493161363417e-05, 1.4277373730075442e-05, 0.0002911148695892433, 0.00010159898819501417, 0.0003412993243803853, 0.0001748642943801907, 0.00030132778059732186, 0.9982328387532813, 0.0003558990551925139, 0.0001625600674925726]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2122222020712618e-05, 7.146041127927606e-06, 0.49963060825061, 5.085182764866702e-05, 0.0001708254651777089, 8.752221963725816e-05, 0.00015081910397846186, 0.49963060825061, 0.0001781328508925179, 8.136376829679537e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[8.084285035686603e-06, 4.765680190991095e-06, 0.3332026292498111, 3.39129796991844e-05, 0.00011392315282550579, 5.8368389004474616e-05, 0.3332026292498111, 0.3332026292498111, 0.00011879643339100625, 5.4261330419865325e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[6.064326401320852e-06, 3.574916034615613e-06, 0.24994782997251627, 2.5439402152370454e-05, 0.24994782997251627, 4.3784324882149415e-05, 0.24994782997251627, 0.24994782997251627, 8.911367476723902e-05, 4.070346569714144e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 578.
Rec Success! in episode: 578.
total combined:  56
-----
It has processed 579 episodes
----target item:  630
[0.9980937728510666, 1.477705383413217e-05, 0.0002812465324538624, 9.750675507420201e-05, 0.0003269766509001921, 0.00017246011590536117, 0.0002952124958545602, 0.00021175507320344376, 0.00034757931064418007, 0.00015871316106355707]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9980937728510666, 1.477705383413217e-05, 0.0002812465324538624, 9.750675507420201e-05, 0.0003269766509001921, 0.00017246011590536117, 0.0002952124958545602, 0.00021175507320344376, 0.00034757931064418007, 0.00015871316106355707]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995473664229129, 7.395936661586442e-06, 0.0001407642933204311, 0.4995473664229129, 0.00016365228326431852, 8.63165356371469e-05, 0.00014775427805548106, 0.00010598371818642334, 0.00017396394404847244, 7.943616500028625e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331633765740465, 4.932575761025772e-06, 0.3331633765740465, 0.3331633765740465, 0.00010914469966444378, 5.756713056655371e-05, 9.854183504702934e-05, 7.068377452513262e-05, 0.00011602186078238761, 5.297840151394814e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2194]
random_location_list [2194]
Random Combined Rec Success! in episode: 579.
Random Combined Rec Success! in episode: 579.
Rec Success! in episode: 579.
total combined:  57
-----
It has processed 580 episodes
----target item:  304
[0.9979618023160908, 1.4923722894806064e-05, 0.0003009010852529989, 0.00010552907869468652, 0.0003522989667377442, 0.00018325266986674867, 0.0003157541183619744, 0.0002255446926636902, 0.0003717800751148001, 0.00016821327432196432]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 580.
Rec Success! in episode: 580.
total combined:  57
-----
It has processed 581 episodes
----target item:  1969
[0.9980053157783493, 1.5389147684044784e-05, 0.0002953380176170184, 0.00010179352182881499, 0.00034193117470469127, 0.00017914903210295276, 0.000308674002662211, 0.00022171896720852053, 0.0003635287857749831, 0.00016716157206717288]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 581.
Rec Success! in episode: 581.
total combined:  57
-----
It has processed 582 episodes
----target item:  1969
[2.4865163177123398e-05, 1.4927042661058442e-05, 0.00028716739615304007, 9.891128063145013e-05, 0.0003320101513714147, 0.00017394453249337067, 0.0002998144215396457, 0.00021538521133165566, 0.9983907265549461, 0.00016224824569501661]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2444381605321649e-05, 7.470605110849594e-06, 0.49966915977832066, 4.950257967264322e-05, 0.00016616263448887097, 8.705481339846159e-05, 0.00015004949076106368, 0.00010779481891435769, 0.49966915977832066, 8.120111940710599e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318902562720126, 4.9815434653478935e-06, 0.33318902562720126, 3.300927416548655e-05, 0.0001108004470509204, 5.804982734027389e-05, 0.00010005589227223242, 7.187966273057492e-05, 0.33318902562720126, 5.414647137136664e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991975196957428, 0.24991975196957428, 0.24991975196957428, 2.4759727895013176e-05, 8.310964082012455e-05, 4.354224579710604e-05, 7.505032235890457e-05, 5.391578383311361e-05, 0.24991975196957428, 4.061440099861093e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 582.
Rec Success! in episode: 582.
total combined:  57
-----
It has processed 583 episodes
----target item:  1969
[2.3188250422604795e-05, 0.9980256971094804, 0.00029118738530251086, 0.00010059416108322433, 0.0003368650818931064, 0.00017674631710265601, 0.00030379522308366454, 0.00021830861692497542, 0.0003583379326612992, 0.0001652799220457432]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3188250422604795e-05, 0.9980256971094804, 0.00029118738530251086, 0.00010059416108322433, 0.0003368650818931064, 0.00017674631710265601, 0.00030379522308366454, 0.00021830861692497542, 0.0003583379326612992, 0.0001652799220457432]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.160616601112084e-05, 0.49953108634385956, 0.0001457448954782124, 0.49953108634385956, 0.00016860746250997325, 8.846493636914929e-05, 0.0001520553611520997, 0.00010926766804361731, 0.00017935503795036626, 8.272578476632318e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.740615897918193e-06, 0.3331572428614787, 0.3331572428614787, 0.3331572428614787, 0.00011245105434144184, 5.9000801144083234e-05, 0.00010141179652004383, 7.287497417979728e-05, 0.0001196190418782621, 5.5173131602321416e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990238701683695, 0.24990238701683695, 0.24990238701683695, 0.24990238701683695, 8.434992035928999e-05, 4.4256702676407435e-05, 7.606933532152545e-05, 5.466376730970184e-05, 8.972665231976881e-05, 4.13855546653896e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 583.
Rec Success! in episode: 583.
total combined:  57
-----
It has processed 584 episodes
----target item:  1969
[2.59057641288431e-05, 1.550402188658692e-05, 0.0003007944402481345, 0.0001035196123383525, 0.00034853829157608485, 0.00018228843380292952, 0.000314840642529832, 0.0002260788469868103, 0.9983129721781563, 0.0001695577683461527]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2965768886440348e-05, 7.759723418773215e-06, 0.4996530968637125, 5.1811301998946984e-05, 0.00017444252615651714, 9.123489628041768e-05, 0.00015757693873832412, 0.00011315188641280966, 0.4996530968637125, 8.486323068266837e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331819991366436, 5.174390347308295e-06, 0.3331819991366436, 3.454915677744744e-05, 0.0001163229247734013, 6.0837859956315515e-05, 0.00010507650166929291, 7.545269299388653e-05, 0.3331819991366436, 5.6589063551342265e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991583483312368, 0.24991583483312368, 0.24991583483312368, 2.5914909512488827e-05, 8.725243539658558e-05, 4.5633751522715656e-05, 7.881662786126588e-05, 5.6596163084551965e-05, 0.24991583483312368, 4.2446780127693246e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 584.
Rec Success! in episode: 584.
total combined:  57
-----
It has processed 585 episodes
----target item:  1818
[0.998144291915221, 1.4107094918578565e-05, 0.0002755270658828118, 9.563845101709914e-05, 0.0003216731423180513, 0.0001653837241246188, 0.00028626414153272043, 0.00020488722005272976, 0.00033636869954557113, 0.00015585854538675625]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 585.
Rec Success! in episode: 585.
total combined:  57
-----
It has processed 586 episodes
----target item:  1506
[0.9980454640467373, 1.4652491088966021e-05, 0.0002896363172137996, 0.00010097746906763851, 0.00033559472353986364, 0.00017469817699308364, 0.0003039116228673167, 0.00021699401718598053, 0.00035625121036787983, 0.0001618199249382904]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 586.
Rec Success! in episode: 586.
total combined:  57
-----
It has processed 587 episodes
----target item:  1843
[2.284522320133052e-05, 0.9980779263701819, 0.00028206448523919664, 9.743691237212268e-05, 0.0003309381357472057, 0.00017021931338855547, 0.0002985231264245043, 0.00021391593994526375, 0.00034770751231859087, 0.00015842298118127744]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 587.
Rec Success! in episode: 587.
total combined:  57
-----
It has processed 588 episodes
----target item:  606
[2.5786693700951195e-05, 1.5017596077059562e-05, 0.0003073079227443482, 0.00010758957691350708, 0.9982554314217096, 0.00018611734487626526, 0.00032194212036615105, 0.00022958063926599467, 0.000380049336485609, 0.00017117734786046095]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2906588213006999e-05, 7.516509513149699e-06, 0.4996403158223575, 5.385003526772641e-05, 0.4996403158223575, 9.315424293916191e-05, 0.0001611363761549226, 0.0001149082083592515, 0.00019021982203423603, 8.567657280344276e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 588.
Rec Success! in episode: 588.
total combined:  57
-----
It has processed 589 episodes
----target item:  1236
[2.517026761894384e-05, 1.4838255749017742e-05, 0.00029226357257501563, 0.00010251968500150312, 0.00034274277437284774, 0.00017659403151559157, 0.000308914058611981, 0.9982104700065756, 0.0003604522020664371, 0.0001660351459130471]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2598247284541836e-05, 7.426858467595586e-06, 0.4996252933638556, 5.131325430207985e-05, 0.00017154995298060513, 8.838901960395405e-05, 0.00015461797065423848, 0.4996252933638556, 0.0001804138932743363, 8.310407572159633e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331695543728494, 4.952517734599644e-06, 0.3331695543728494, 3.4217671315519946e-05, 0.00011439617278464681, 5.894123188726621e-05, 0.00010310526921900951, 0.3331695543728494, 0.00012030699250669652, 5.541702600426194e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990879138948022, 0.24990879138948022, 0.24990879138948022, 2.5666501546699962e-05, 8.580798847003823e-05, 4.4211518821643444e-05, 7.733873902407644e-05, 0.24990879138948022, 9.024166433708775e-05, 4.15680298795426e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 589.
Rec Success! in episode: 589.
total combined:  57
-----
It has processed 590 episodes
----target item:  1490
[0.9980752703723034, 1.4437525872068153e-05, 0.0002855047948917281, 9.934377759995203e-05, 0.0003338131406863772, 0.000171990667458032, 0.00029865561664137153, 0.00021226450156076074, 0.0003498543431832901, 0.00015886525980304546]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 590.
Rec Success! in episode: 590.
total combined:  57
-----
It has processed 591 episodes
----target item:  1692
[0.9980686434883634, 1.4469003653261646e-05, 0.00028288718212909935, 9.858193079658033e-05, 0.0003332676727180877, 0.0001728152673272451, 0.00030018034569317687, 0.00021478637277607597, 0.00035250717043291063, 0.00016186156611017777]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 591.
Rec Success! in episode: 591.
total combined:  57
-----
It has processed 592 episodes
----target item:  222
[2.6512643583185713e-05, 1.5547788264324445e-05, 0.00030261571598188744, 0.00010550841028677564, 0.0003528708245342321, 0.9981213354217607, 0.00031283684184733906, 0.00022333047013939052, 0.0003694847129037227, 0.00016995717069821109]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 592.
Rec Success! in episode: 592.
total combined:  57
-----
It has processed 593 episodes
----target item:  354
[2.55791729054524e-05, 1.5284009384641364e-05, 0.00030941340274540975, 0.000107942191291297, 0.9982556502720243, 0.0001879648305886969, 0.0003191132773287319, 0.0002282311463234463, 0.00037848994455471843, 0.00017233175285329486]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.280273334358295e-05, 7.64986019273018e-06, 0.4996408971626086, 5.402657453908226e-05, 0.4996408971626086, 9.407902330907165e-05, 0.00015972065285839356, 0.00011423287679706414, 0.00018943950421198552, 8.625444953080092e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 593.
Rec Success! in episode: 593.
total combined:  57
-----
It has processed 594 episodes
----target item:  375
[2.2426589191967166e-05, 0.9980785972642506, 0.00028335183707504864, 9.845068271800948e-05, 0.000329809228918032, 0.00017053712544634123, 0.00029803628317283696, 0.00021143811286269135, 0.00034922359509987423, 0.00015812928126455227]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 594.
Rec Success! in episode: 594.
total combined:  57
-----
It has processed 595 episodes
----target item:  478
[0.9979685843174081, 1.4872462806902298e-05, 0.0002989344485362835, 0.00010583676503025928, 0.000349782276205808, 0.0001807240894891538, 0.0003159967001409896, 0.00022443863469164392, 0.00036987616368153967, 0.00017095414200918302]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 595.
Rec Success! in episode: 595.
total combined:  57
-----
It has processed 596 episodes
----target item:  25
[2.4568888400598498e-05, 1.5143458905275522e-05, 0.0002731546948401388, 9.467485713088489e-05, 0.00031839078334142546, 0.0001645096067436668, 0.0002871340330126457, 0.00020516983728089032, 0.998464379720868, 0.00015287411947648865]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2295564154666162e-05, 7.57858342865972e-06, 0.49968409790602614, 4.738027869662558e-05, 0.0001593394963173648, 8.232926092522699e-05, 0.0001436969742517539, 0.00010267777913909006, 0.49968409790602614, 7.650625103435601e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331956346220052, 5.053494649179298e-06, 0.3331956346220052, 3.159376513090201e-05, 0.00010624957812005398, 5.48981855874482e-05, 9.581894787069962e-05, 6.84668331956029e-05, 0.3331956346220052, 5.101532943066922e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992348381298374, 0.24992348381298374, 0.24992348381298374, 2.3697861039631766e-05, 7.969571614450541e-05, 4.117804788346605e-05, 7.18719058078511e-05, 5.1355623243082636e-05, 0.24992348381298374, 3.826559394646358e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 596.
Rec Success! in episode: 596.
total combined:  57
-----
It has processed 597 episodes
----target item:  1809
[0.9980268300724, 1.498019333714296e-05, 0.00029076033380840696, 0.00010258248834315219, 0.0003441796365653925, 0.0001767833113265759, 0.00030268838846523043, 0.00021738369519236527, 0.0003596938552106601, 0.00016411802535078098]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 597.
Rec Success! in episode: 597.
total combined:  57
-----
It has processed 598 episodes
----target item:  1473
[2.2727955507058527e-05, 0.9980225885570942, 0.0002923334650769541, 0.00010061301270391047, 0.00033873263824939686, 0.00017665542826402443, 0.00030709978395911976, 0.00021775368331547178, 0.00035839267293406537, 0.00016310280289572604]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2727955507058527e-05, 0.9980225885570942, 0.0002923334650769541, 0.00010061301270391047, 0.00033873263824939686, 0.00017665542826402443, 0.00030709978395911976, 0.00021775368331547178, 0.00035839267293406537, 0.00016310280289572604]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1300365052497007e-05, 0.49952971713507144, 0.00014646961398042286, 0.49952971713507144, 0.000169907228349442, 8.849475401234853e-05, 0.00015380191603634475, 0.00010902038143789628, 0.00017955658957723275, 8.201488141068176e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[7.536675543880953e-06, 0.33315679494281186, 0.33315679494281186, 0.33315679494281186, 0.00011331807837012132, 5.902077014576203e-05, 0.00010257678701601027, 7.271015040226582e-05, 0.00011975363195106463, 5.4699078135143774e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[5.653563514753519e-06, 0.24991431429075361, 0.24991431429075361, 0.24991431429075361, 8.500444920379305e-05, 4.427385400445529e-05, 7.694697445284085e-05, 0.24991431429075361, 8.983201683764223e-05, 4.1031978972025326e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.19994606177490207, 0.19994606177490207, 0.19994606177490207, 0.19994606177490207, 6.800852884268727e-05, 3.5421671515337184e-05, 6.156207799061934e-05, 0.19994606177490207, 7.187086517616011e-05, 3.282798196481936e-05]
[-1, 1, 0, 0, 1, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 598.
Rec Success! in episode: 598.
total combined:  57
-----
It has processed 599 episodes
----target item:  505
[0.9980688106313721, 1.53916395026186e-05, 0.00028604375113094096, 9.977714309348189e-05, 0.00033353146774251646, 0.00017347612644051354, 0.0002960666842871519, 0.0002150818575817414, 0.0003507951273923068, 0.0001610255714569257]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2184]
random_location_list [2184]
Random Combined Rec Success! in episode: 599.
Random Combined Rec Success! in episode: 599.
Rec Success! in episode: 599.
total combined:  58
-----
It has processed 600 episodes
----target item:  1406
[2.6838524893200867e-05, 1.550694165096507e-05, 0.00031144480382136225, 0.9979872858652394, 0.0003634727542236677, 0.00018625560822759004, 0.00032349983943009156, 0.00023285818892146713, 0.0003797492032613966, 0.00017308827033077722]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49950302429347115, 7.761385702909018e-06, 0.0001558813660380278, 0.49950302429347115, 0.00018192189675602285, 9.322287059062185e-05, 0.00016191503683705527, 0.00011654794729867868, 0.00019006842891555376, 8.66324809188238e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 600.
Rec Success! in episode: 600.
total combined:  58
-----
It has processed 601 episodes
----target item:  373
[0.9980411614822947, 1.426001351359834e-05, 0.00028922255577761073, 0.00010115370258684914, 0.00033926730320169826, 0.0001748687489909507, 0.00030478668148789853, 0.00021735930956677388, 0.0003557151401978096, 0.0001622050623822492]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9980411614822947, 1.426001351359834e-05, 0.00028922255577761073, 0.00010115370258684914, 0.00033926730320169826, 0.0001748687489909507, 0.00030478668148789853, 0.00021735930956677388, 0.0003557151401978096, 0.0001622050623822492]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995350999509781, 7.137358207990117e-06, 0.00014476038051764175, 0.4995350999509781, 0.0001698085537506818, 8.752452441516533e-05, 0.00015255046713169584, 0.00010879170982131901, 0.00017804095158648555, 8.11861526125132e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331588091291044, 4.760173531620057e-06, 0.3331588091291044, 0.3331588091291044, 0.00011325173256706982, 5.8373408248207746e-05, 0.0001017416633319099, 7.255729675601701e-05, 0.0001187422293500237, 5.414610890168272e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331588091291044, 4.760173531620057e-06, 0.3331588091291044, 0.3331588091291044, 0.00011325173256706982, 5.8373408248207746e-05, 0.0001017416633319099, 7.255729675601701e-05, 0.0001187422293500237, 5.414610890168272e-05]
[-1, 0, 0, -1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331588091291044, 4.760173531620057e-06, 0.3331588091291044, 0.3331588091291044, 0.00011325173256706982, 5.8373408248207746e-05, 0.0001017416633319099, 7.255729675601701e-05, 0.0001187422293500237, 5.414610890168272e-05]
[-1, 0, 0, -1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331588091291044, 4.760173531620057e-06, 0.3331588091291044, 0.3331588091291044, 0.00011325173256706982, 5.8373408248207746e-05, 0.0001017416633319099, 7.255729675601701e-05, 0.0001187422293500237, 5.414610890168272e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([6], dtype=torch.int32)
[0.24991997034492155, 3.63672276913446e-06, 0.24991997034492155, 0.24991997034492155, 8.587511011921782e-05, 4.440056793009512e-05, 0.24991997034492155, 5.50335097182479e-05, 9.011901191579712e-05, 4.10536978612692e-05]
[-1, 0, 0, -1, -1, -1, 1, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 601.
Rec Success! in episode: 601.
total combined:  58
-----
It has processed 602 episodes
----target item:  203
[2.579422953551225e-05, 1.5162797004107637e-05, 0.0002983534940701775, 0.9980656880241796, 0.0003466199578790294, 0.00017899709288789632, 0.0003119634337516432, 0.00022229890861957946, 0.0003668666247183906, 0.0001682554373542042]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49952240249250973, 7.5888359642863315e-06, 0.00014932309159430723, 0.49952240249250973, 0.00017347999855034653, 8.958634582012676e-05, 0.00015613473720945957, 0.00011125849354158443, 0.00018361326310739653, 8.421024919310107e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33315568933022893, 5.0613623418696555e-06, 9.959080366524363e-05, 0.33315568933022893, 0.0001157022151832609, 5.9749473992266335e-05, 0.33315568933022893, 7.420367920384751e-05, 0.00012246058021718988, 5.6163894709444245e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.2499187316261246, 3.796811212569385e-06, 0.2499187316261246, 0.2499187316261246, 8.679470827307822e-05, 4.482142503853203e-05, 0.2499187316261246, 5.5664333470935965e-05, 9.186453619809881e-05, 4.213168130847802e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.19996187026748313, 3.037857411399258e-06, 0.19996187026748313, 0.19996187026748313, 0.19996187026748313, 3.5861961688276194e-05, 0.19996187026748313, 4.45374548582964e-05, 7.350151127090044e-05, 3.370987735549218e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.16664637204528865, 2.531722251464168e-06, 0.16664637204528865, 0.16664637204528865, 0.16664637204528865, 2.9887026970612386e-05, 0.16664637204528865, 0.16664637204528865, 6.12554792409005e-05, 2.8093499805087156e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 602.
Rec Success! in episode: 602.
total combined:  58
-----
It has processed 603 episodes
----target item:  409
[2.5359862462060417e-05, 1.4748275648577464e-05, 0.0002908301020888507, 0.00010021064109748505, 0.998337363825062, 0.00017783013505172178, 0.00030961366969237385, 0.00021983532293761235, 0.00036124886757478095, 0.0001629592983845353]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2692328248635543e-05, 7.3813474309314045e-06, 0.4996567131821768, 5.015430792333046e-05, 0.4996567131821768, 8.90019987274119e-05, 0.00015495818764314198, 0.00011002512665608032, 0.0001808010281430551, 8.155931087395257e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2178]
random_location_list [2178]
Random Combined Rec Success! in episode: 603.
Random Combined Rec Success! in episode: 603.
Rec Success! in episode: 603.
total combined:  59
-----
It has processed 604 episodes
----target item:  1785
[2.5183825709671877e-05, 1.4515901463080934e-05, 0.00029319784469578145, 0.9980870857332967, 0.0003447984773038063, 0.00017710102420246128, 0.00030928794461606337, 0.0002195008161656021, 0.0003637298767271168, 0.00016559855581972055]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995276096203047, 7.264990864007931e-06, 0.0001467411216919055, 0.4995276096203047, 0.00017256646401926821, 8.863640512507626e-05, 0.00015479397526211794, 0.00010985686477282838, 0.00018204134535564542, 8.28795922997283e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33315770728136335, 4.845353195817728e-06, 9.786833545383191e-05, 0.33315770728136335, 0.00011509243212804861, 5.911565435908223e-05, 0.33315770728136335, 7.326854510535264e-05, 0.00012141166190033246, 5.527617376741142e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991954415549805, 3.6347604618027454e-06, 0.24991954415549805, 0.24991954415549805, 8.633703361662718e-05, 4.4345837022460115e-05, 0.24991954415549805, 5.4962682817965825e-05, 9.107742829934499e-05, 4.1465635789553116e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.19996231715671348, 2.9081964226033643e-06, 0.19996231715671348, 0.19996231715671348, 0.19996231715671348, 3.548140405436962e-05, 0.19996231715671348, 4.397601416314902e-05, 7.287166621942961e-05, 3.317693557289958e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.16664660444002494, 2.423661946723982e-06, 0.16664660444002494, 0.16664660444002494, 0.16664660444002494, 2.956984891203895e-05, 0.16664660444002494, 0.16664660444002494, 6.073052117033392e-05, 2.7649327821182254e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 604.
Rec Success! in episode: 604.
total combined:  59
-----
It has processed 605 episodes
----target item:  1785
[2.643961954431933e-05, 1.5286593529060124e-05, 0.0003035920991380934, 0.9980200268223168, 0.000357087207830921, 0.00018318554614509973, 0.00031988520813245426, 0.0002270466626724339, 0.0003759786112060909, 0.0001714716294846857]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995111261691101, 7.650972268865805e-06, 0.00015194848526172095, 0.4995111261691101, 0.0001787228998721911, 9.168475180221316e-05, 0.0001601032206416135, 0.00011363733303583991, 0.00018817808706406706, 8.582191183343542e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331515559223905, 5.102855936844059e-06, 0.00010134283629120737, 0.3331515559223905, 0.00011920017203225243, 6.114962433674499e-05, 0.3331515559223905, 7.579101310937348e-05, 0.00012550635854038738, 5.7239372581790044e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991673430749667, 3.827954781261098e-06, 0.24991673430749667, 0.24991673430749667, 8.941911629592418e-05, 4.5871958712777645e-05, 0.24991673430749667, 5.685533250387641e-05, 9.41497606829317e-05, 4.293864703661621e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.1999610116292457, 3.0627869424309153e-06, 0.1999610116292457, 0.1999610116292457, 0.1999610116292457, 3.670263736055414e-05, 0.1999610116292457, 4.5490550424702934e-05, 7.533021525339963e-05, 3.43556637902792e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.166645908079816, 2.5525021458820884e-06, 0.166645908079816, 0.166645908079816, 0.166645908079816, 3.058768447928359e-05, 0.166645908079816, 0.166645908079816, 6.277959900516303e-05, 2.863173547366958e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 605.
Rec Success! in episode: 605.
total combined:  59
-----
It has processed 606 episodes
----target item:  1462
[0.9980727018678011, 1.4572933323726874e-05, 0.00028449794199101566, 0.00010034558120719383, 0.0003331913580198071, 0.00017215278488998738, 0.0002985868597565088, 0.00021468138835305828, 0.0003491877013432162, 0.00016008158331445171]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 606.
Rec Success! in episode: 606.
total combined:  59
-----
It has processed 607 episodes
----target item:  103
[2.2779317447186756e-05, 0.9980557154132587, 0.0002859677685294518, 9.85649692202069e-05, 0.0003370783596200002, 0.00017258417049032093, 0.0002999230013337317, 0.00021516404672065044, 0.00035341093989594544, 0.0001588120134839711]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 607.
Rec Success! in episode: 607.
total combined:  59
-----
It has processed 608 episodes
----target item:  609
[2.5726085873203023e-05, 1.4753553631067247e-05, 0.00030117064226382726, 0.00010397834263278828, 0.00035149967052866917, 0.00018022851884765256, 0.9982594157307235, 0.000225035714188057, 0.0003700176827654022, 0.0001681740585458932]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2876187946592446e-05, 7.384315296546165e-06, 0.49963977885159727, 5.204230012734056e-05, 0.00017592943766104905, 9.020634905194072e-05, 0.49963977885159727, 0.00011263284142261617, 0.00018519790574953663, 8.417295954973636e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.333176057300741, 4.924101643835596e-06, 0.333176057300741, 3.470349860682184e-05, 0.00011731547183406859, 6.0152527866574944e-05, 0.333176057300741, 7.510724248981977e-05, 0.00012349598784910197, 5.61292674866179e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499124448496322, 0.2499124448496322, 0.2499124448496322, 2.6030790603413997e-05, 8.799730875702105e-05, 4.5119884738452184e-05, 0.2499124448496322, 5.6337285303793915e-05, 9.263325973219896e-05, 4.2102072336301856e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 608.
Rec Success! in episode: 608.
total combined:  59
-----
It has processed 609 episodes
----target item:  466
[2.3739374243778634e-05, 0.998067865616703, 0.00028348055109010407, 9.987800396843594e-05, 0.0003319155400259998, 0.00017188352057414955, 0.0002972374016931914, 0.00021243916519904702, 0.0003508187270125173, 0.00016074209948978968]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 609.
Rec Success! in episode: 609.
total combined:  59
-----
It has processed 610 episodes
----target item:  653
[0.9979926796381683, 1.561244987479444e-05, 0.0002985239794512439, 0.00010314945631812517, 0.0003449951564165229, 0.00017925689605318695, 0.00030906382392838834, 0.00022314019682537073, 0.00036560108644265844, 0.00016797731652136707]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 610.
Rec Success! in episode: 610.
total combined:  59
-----
It has processed 611 episodes
----target item:  676
[0.9981198397884861, 1.447305193373053e-05, 0.0002751287937756594, 9.697080200708108e-05, 0.0003253903814056813, 0.00016906048865257425, 0.00029097166062942313, 0.00020900073263672734, 0.000341965027372375, 0.00015719927310072943]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 611.
Rec Success! in episode: 611.
total combined:  59
-----
It has processed 612 episodes
----target item:  108
[2.280559329702573e-05, 0.9980303278790357, 0.00028932501126099924, 0.00010024255853314132, 0.0003393049828305124, 0.0001750513496489485, 0.0003041878479775325, 0.00021701513306203753, 0.00035779747957911836, 0.00016394216477487675]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 612.
Rec Success! in episode: 612.
total combined:  59
-----
It has processed 613 episodes
----target item:  1255
[2.3263161528855366e-05, 0.9981052338747127, 0.00028114250013363276, 9.757436266852103e-05, 0.0003257806175736381, 0.00016813795335845837, 0.00029070767891776, 0.00020885677067922302, 0.00034174762085724175, 0.0001575554595699569]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 613.
Rec Success! in episode: 613.
total combined:  59
-----
It has processed 614 episodes
----target item:  1606
[2.2868743681324027e-05, 0.9980924233762546, 0.0002813089474352606, 9.74837855163214e-05, 0.00032878916644412905, 0.00017056718683455759, 0.00029476505116069997, 0.00020955004570303098, 0.0003455051291571156, 0.00015673856781302155]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2868743681324027e-05, 0.9980924233762546, 0.0002813089474352606, 9.74837855163214e-05, 0.00032878916644412905, 0.00017056718683455759, 0.00029476505116069997, 0.00020955004570303098, 0.0003455051291571156, 0.00015673856781302155]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.144584664764385e-05, 0.4995470226669844, 0.00014079562558495912, 0.4995470226669844, 0.00016455955915057374, 8.536917859736719e-05, 0.00014753042929181717, 0.00010488016838819142, 0.00017292592804458632, 7.844793032615353e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.63358617646172e-06, 0.33316323065609865, 0.33316323065609865, 0.33316323065609865, 0.00010974981708277923, 5.693532350190119e-05, 9.839256809205166e-05, 6.994780100062611e-05, 0.00011532960509694596, 5.231933075331128e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990573597586202, 0.24990573597586202, 0.24990573597586202, 0.24990573597586202, 8.232333669377604e-05, 4.270718558811632e-05, 7.38042643396644e-05, 5.2467844829486504e-05, 8.650873562727659e-05, 3.924472947366488e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 614.
Rec Success! in episode: 614.
total combined:  59
-----
It has processed 615 episodes
----target item:  1606
[2.7019782332679016e-05, 1.547062634469703e-05, 0.00031577525487988956, 0.00010997179719224269, 0.9982073252788893, 0.00019151787438589088, 0.0003317146252373631, 0.00023533198117971191, 0.00038902646255693427, 0.00017684631700115537]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3524148661800143e-05, 7.743476538809685e-06, 0.49963038547657584, 5.5043927279697005e-05, 0.49963038547657584, 9.585999519522938e-05, 0.00016603234806883128, 0.00011779016792822608, 0.00019471850839564302, 8.851647478014019e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 615.
Rec Success! in episode: 615.
total combined:  59
-----
It has processed 616 episodes
----target item:  74
[2.3267587127643415e-05, 0.9980188407555274, 0.00028938675608546, 0.00010302668780243363, 0.0003409766268947405, 0.00017699022828181356, 0.00030464702309223647, 0.00021897395128573385, 0.00035832954264889734, 0.0001655608412535918]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 616.
Rec Success! in episode: 616.
total combined:  59
-----
It has processed 617 episodes
----target item:  1660
[2.3066277015331933e-05, 0.9979790745611788, 0.00030013197892895887, 0.00010212610498715173, 0.0003449095276014097, 0.00018062035886607077, 0.0003131359430850334, 0.00022294695503755467, 0.00036711713009576123, 0.00016687116320343373]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 617.
Rec Success! in episode: 617.
total combined:  59
-----
It has processed 618 episodes
----target item:  70
[2.615734690511955e-05, 1.5218475124888005e-05, 0.000299846874124258, 0.9980318800786866, 0.0003526335563191241, 0.00018319753890810238, 0.0003186239598532742, 0.000228645142726088, 0.0003726962211600254, 0.00017110080619261282]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.49951402477172246, 7.6168326004995014e-06, 0.0001500730807288635, 0.49951402477172246, 0.00017649276591509677, 9.169019729214026e-05, 0.0001594709946163889, 0.00011443668059842789, 0.00018653411094861875, 8.563579385482164e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331527046177099, 5.080074343531036e-06, 0.00010009178973099206, 0.3331527046177099, 0.00011771249533373157, 6.115311222496272e-05, 0.3331527046177099, 7.632396240778687e-05, 0.00012440960710641152, 5.711510572272038e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.2499171461139478, 3.8108580971564277e-06, 0.2499171461139478, 0.2499171461139478, 8.830296283956313e-05, 4.587449260178157e-05, 0.2499171461139478, 5.725502630077807e-05, 9.332685440110661e-05, 4.284534996826166e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.19994757961582282, 0.19994757961582282, 0.19994757961582282, 0.19994757961582282, 7.064726837360127e-05, 3.6702138706593854e-05, 0.19994757961582282, 4.580719693582458e-05, 7.466666029449403e-05, 3.427865657541085e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16663819312485043, 0.16663819312485043, 0.16663819312485043, 0.16663819312485043, 0.16663819312485043, 3.2799638503833934e-05, 0.16663819312485043, 4.0838792920319516e-05, 6.669193295207055e-05, 3.0510886521125052e-05]
[1, 0, 0, 1, 1, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2130]
random_location_list [2130]
Random Combined Rec Success! in episode: 618.
Random Combined Rec Success! in episode: 618.
Rec Success! in episode: 618.
total combined:  60
-----
It has processed 619 episodes
----target item:  1011
[2.619221603638656e-05, 1.5309723440685567e-05, 0.0003085692733366877, 0.0001075625762166397, 0.9982613860430952, 0.00018542967131819242, 0.0003208176695397722, 0.00022844105805203523, 0.0003760581673476236, 0.00017023360161686133]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3109526819924357e-05, 7.662705201135809e-06, 0.49964212250870865, 5.383639459041093e-05, 0.49964212250870865, 9.280983502803165e-05, 0.00016057319614707537, 0.00011433756399781912, 0.00018822174587467252, 8.520401492368117e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 619.
Rec Success! in episode: 619.
total combined:  60
-----
It has processed 620 episodes
----target item:  432
[0.9980138196904735, 1.5426253772679883e-05, 0.00029266399242260625, 0.00010226846409503451, 0.0003434089395914657, 0.00017799887744358956, 0.0003078960643495642, 0.00021895350128999766, 0.00036203723502102256, 0.00016552698154053704]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 620.
Rec Success! in episode: 620.
total combined:  60
-----
It has processed 621 episodes
----target item:  809
[2.4016563254697104e-05, 1.3760705288868199e-05, 0.00028163533150885224, 9.850239340366136e-05, 0.9983890956806618, 0.0001718807203898903, 0.000298745306465543, 0.0002121107696307949, 0.0003490910470513087, 0.00016116148234450328]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2019655464626718e-05, 6.886869481215805e-06, 0.49966736799341194, 4.929784576573719e-05, 0.49966736799341194, 8.602175999075424e-05, 0.00014951413394619914, 0.00010615583688063019, 0.00017471084712846624, 8.065706451861286e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 621.
Rec Success! in episode: 621.
total combined:  60
-----
It has processed 622 episodes
----target item:  782
[2.5005139522982596e-05, 1.4951445713747844e-05, 0.0002810792513810746, 9.607793791392618e-05, 0.9984052175069845, 0.00016936154074845866, 0.0002954184369459597, 0.00020999973407422935, 0.00034619231695852615, 0.0001566966897564826]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2514307316667778e-05, 7.482741150807933e-06, 0.49967126585969246, 4.808406848926006e-05, 0.49967126585969246, 8.476026964786791e-05, 0.00014784788957299973, 0.00010509844211059015, 0.0001732586631282869, 7.842189919855604e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 622.
Rec Success! in episode: 622.
total combined:  60
-----
It has processed 623 episodes
----target item:  919
[2.4311855369094343e-05, 1.4651482415413471e-05, 0.00027949546722070504, 9.683528448611769e-05, 0.00032626581400581025, 0.00016910894493532682, 0.9983796623957609, 0.00020972611698065886, 0.00034290494910779257, 0.0001570376897181058]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2167485780488313e-05, 7.332706667021395e-06, 0.49966447074095394, 4.846367869283146e-05, 0.00016328801699033076, 8.46348685287782e-05, 0.49966447074095394, 0.00010496276435582694, 0.00017161549495033705, 7.85935021263236e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318687915617035, 4.889604511062254e-06, 0.33318687915617035, 3.2316610048632806e-05, 0.00010888391704923517, 5.643632750409423e-05, 0.33318687915617035, 6.999140009186982e-05, 0.00011443685618181311, 5.2407816102257226e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991852707837667, 0.24991852707837667, 0.24991852707837667, 2.4240208990147462e-05, 8.167220822256396e-05, 4.2332050647543946e-05, 0.24991852707837667, 5.249950917459327e-05, 8.583738535224101e-05, 3.931032410652477e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 623.
Rec Success! in episode: 623.
total combined:  60
-----
It has processed 624 episodes
----target item:  874
[2.6309088083332313e-05, 1.5032868825918304e-05, 0.0003071359224050739, 0.00010882362135952752, 0.0003598026838753411, 0.00018532599315771586, 0.00032265803536244797, 0.9981252721472712, 0.0003776073389174228, 0.00017203230074193976]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3168910425974364e-05, 7.524643286262703e-06, 0.4996076740164933, 5.4471235087075404e-05, 0.0001800978163884499, 9.276419599829697e-05, 0.00016150520886358143, 0.4996076740164933, 0.00018900986634897625, 8.611009061466269e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33316184629601303, 5.0177853150578725e-06, 0.33316184629601303, 3.632397618262986e-05, 0.00012009767692214332, 6.185951981181453e-05, 0.00010769925357399069, 0.33316184629601303, 0.0001260406501260202, 5.7422250029231775e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990446672969174, 0.24990446672969174, 0.24990446672969174, 2.724658900274191e-05, 9.00851830435489e-05, 4.6400782330252416e-05, 8.078513440485781e-05, 0.24990446672969174, 9.454300306650592e-05, 4.3072389385260537e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 624.
Rec Success! in episode: 624.
total combined:  60
-----
It has processed 625 episodes
----target item:  950
[2.2997840886297625e-05, 0.998083447585463, 0.0002838990572710007, 9.985057954973249e-05, 0.0003306539501562922, 0.00017068308360174215, 0.0002957446516026004, 0.00020981564370912867, 0.000346216178916662, 0.00015669142884381566]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2997840886297625e-05, 0.998083447585463, 0.0002838990572710007, 9.985057954973249e-05, 0.0003306539501562922, 0.00017068308360174215, 0.0002957446516026004, 0.00020981564370912867, 0.000346216178916662, 0.00015669142884381566]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1510525372060677e-05, 0.49954536617875384, 0.00014209278679586698, 0.49954536617875384, 0.00016549382620147384, 8.54276701057606e-05, 0.00014802156136105906, 0.00010501369682090921, 0.00017328279343007904, 7.842478240493376e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.67673752373603e-06, 0.3331627821837948, 0.3331627821837948, 0.3331627821837948, 0.00011037312585498952, 5.697444551558547e-05, 9.872031359929202e-05, 7.003699317218821e-05, 0.000115567837222389, 5.230399572726076e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990549173366386, 0.24990549173366386, 0.24990549173366386, 0.24990549173366386, 8.279091112811089e-05, 4.273654677001247e-05, 7.405013354859831e-05, 5.253476724956431e-05, 8.668746550965119e-05, 3.923324113869864e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990549173366386, 0.24990549173366386, 0.24990549173366386, 0.24990549173366386, 8.279091112811089e-05, 4.273654677001247e-05, 7.405013354859831e-05, 5.253476724956431e-05, 8.668746550965119e-05, 3.923324113869864e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990549173366386, 0.24990549173366386, 0.24990549173366386, 0.24990549173366386, 8.279091112811089e-05, 4.273654677001247e-05, 7.405013354859831e-05, 5.253476724956431e-05, 8.668746550965119e-05, 3.923324113869864e-05]
[-1, 0, 0, 1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 625.
Rec Success! in episode: 625.
total combined:  60
-----
It has processed 626 episodes
----target item:  761
[2.309944162361358e-05, 0.9980142591426717, 0.0002925421574092504, 0.00010183807316387674, 0.0003416181117150446, 0.00017797952590084087, 0.0003058083196866329, 0.0002176378970367562, 0.00035954476271362424, 0.0001656725680782275]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.309944162361358e-05, 0.9980142591426717, 0.0002925421574092504, 0.00010183807316387674, 0.0003416181117150446, 0.00017797952590084087, 0.0003058083196866329, 0.0002176378970367562, 0.00035954476271362424, 0.0001656725680782275]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1561788885244611e-05, 0.49952853219082666, 0.00014642391444398198, 0.49952853219082666, 0.00017098753084090253, 8.908274658283882e-05, 0.0001530639263571573, 0.00010893265127219738, 0.00017996022194063718, 8.292283802387141e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.7110356469009e-06, 0.33315625779012437, 0.33315625779012437, 0.33315625779012437, 0.00011403866292459737, 5.941297157750139e-05, 0.00010208466908619592, 7.265169476873451e-05, 0.00012002292207388733, 5.530467354928992e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 8.554085229453398e-05, 4.456590506897452e-05, 7.657411421609313e-05, 5.4496323718466e-05, 9.002966876127996e-05, 4.148425446206126e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 8.554085229453398e-05, 4.456590506897452e-05, 7.657411421609313e-05, 5.4496323718466e-05, 9.002966876127996e-05, 4.148425446206126e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 8.554085229453398e-05, 4.456590506897452e-05, 7.657411421609313e-05, 5.4496323718466e-05, 9.002966876127996e-05, 4.148425446206126e-05]
[-1, 0, 0, 1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 8.554085229453398e-05, 4.456590506897452e-05, 7.657411421609313e-05, 5.4496323718466e-05, 9.002966876127996e-05, 4.148425446206126e-05]
[-1, 0, 0, 1, -1, -1, -1, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 8.554085229453398e-05, 4.456590506897452e-05, 7.657411421609313e-05, 5.4496323718466e-05, 9.002966876127996e-05, 4.148425446206126e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 0.2499018272203697, 8.554085229453398e-05, 4.456590506897452e-05, 7.657411421609313e-05, 5.4496323718466e-05, 9.002966876127996e-05, 4.148425446206126e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  60
-----
It has processed 627 episodes
----target item:  894
[2.3981595425632352e-05, 1.4411093703030513e-05, 0.00026786206235693445, 9.272871948977345e-05, 0.9984774419309423, 0.0001626827167261962, 0.0002802401631671969, 0.00020297462908638633, 0.000328571810766315, 0.00014910527833613454]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.200154161367274e-05, 7.212003109292607e-06, 0.4996860449425973, 4.640590277616018e-05, 0.4996860449425973, 8.141424121132239e-05, 0.0001402456308840373, 0.00010157824841362997, 0.0001644331075561773, 7.46194392411734e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 627.
Rec Success! in episode: 627.
total combined:  60
-----
It has processed 628 episodes
----target item:  588
[2.473097676213633e-05, 0.9978719533710967, 0.00031254529314674105, 0.00010886484042531649, 0.00036742474852909237, 0.0001917700599942425, 0.00032701796245075156, 0.0002335085778798605, 0.00038578023759272263, 0.00017640393212253709]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 628.
Rec Success! in episode: 628.
total combined:  60
-----
It has processed 629 episodes
----target item:  246
[0.9980497927670379, 1.453942809253569e-05, 0.0002876593222628178, 9.965276374950811e-05, 0.00033852072417138207, 0.0001746892941728991, 0.0003012119635189924, 0.0002156106529875518, 0.00035515077191976556, 0.0001631723120865367]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 629.
Rec Success! in episode: 629.
total combined:  60
-----
It has processed 630 episodes
----target item:  133
[0.9979835740721335, 1.510911481532626e-05, 0.00029879247768250345, 0.00010477878359779577, 0.0003474295253870359, 0.0001802089969187497, 0.0003123866134691668, 0.00022506876124567187, 0.00036634482112890337, 0.00016630683362116265]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 630.
Rec Success! in episode: 630.
total combined:  60
-----
It has processed 631 episodes
----target item:  1547
[2.6094288988648632e-05, 1.5015752499019093e-05, 0.00029227442940485437, 0.0001028384273407377, 0.00034325739598864327, 0.0001759596355479804, 0.9982985558658011, 0.0002193812307776763, 0.00036027472156557026, 0.00016634825208592193]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.306016363967037e-05, 7.515368013870329e-06, 0.4996473560373941, 5.1470522538500534e-05, 0.0001717999583774433, 8.806760878723584e-05, 0.4996473560373941, 0.00010980007060836658, 0.00018031711156912047, 8.325712167748125e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331794674289421, 5.011467152057587e-06, 0.3331794674289421, 3.432204950241652e-05, 0.00011456123592942034, 5.872605676567545e-05, 0.3331794674289421, 7.321789779713735e-05, 0.00012024072273171081, 5.5518283295176244e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499143798765459, 0.2499143798765459, 0.2499143798765459, 2.5744604803169307e-05, 8.593116633544606e-05, 4.4049791460569816e-05, 0.2499143798765459, 5.491996750291461e-05, 9.01912890649902e-05, 4.164367464955949e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 631.
Rec Success! in episode: 631.
total combined:  60
-----
It has processed 632 episodes
----target item:  1289
[0.997999605272999, 1.500671459385515e-05, 0.00029514526737199425, 0.00010148046080595162, 0.0003454204612192787, 0.000179397641806984, 0.00031084522835597754, 0.00022028772363378546, 0.00036718831492964276, 0.00016562291428394796]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 632.
Rec Success! in episode: 632.
total combined:  60
-----
It has processed 633 episodes
----target item:  850
[0.9979419640872927, 1.4896885372100768e-05, 0.00030324594018633607, 0.00010781904918588107, 0.00035734799943905646, 0.00018509149994302255, 0.00031863503551314966, 0.00022539079039371576, 0.0003753864967665393, 0.00017022221590739882]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 633.
Rec Success! in episode: 633.
total combined:  60
-----
It has processed 634 episodes
----target item:  73
[2.4750187658508967e-05, 1.4152143413182847e-05, 0.00028426897358870457, 9.903664386473757e-05, 0.9983861375629542, 0.00017197047354470778, 0.00029770964076176337, 0.0002116759675107148, 0.0003486887557483002, 0.0001616096509550237]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2386849763562e-05, 7.082793743230961e-06, 0.49966728586656217, 4.956536271829634e-05, 0.49966728586656217, 8.606691993442597e-05, 0.0001489962275907097, 0.00010593852637761427, 0.00017450999932974894, 8.088158741832222e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 634.
Rec Success! in episode: 634.
total combined:  60
-----
It has processed 635 episodes
----target item:  60
[2.5958956849103397e-05, 1.5133525694111035e-05, 0.0003033655695484767, 0.9980302109042173, 0.00035215323428461137, 0.00018346257958257287, 0.0003196585456665671, 0.00022652191581030255, 0.0003729022191048043, 0.00017063254924188119]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4995135570564882, 7.574321065313575e-06, 0.00015183429627479498, 0.4995135570564882, 0.00017625249492906884, 9.182291749567595e-05, 0.0001599889216226692, 0.00011337409096578326, 0.00018663735011642383, 8.54014945541648e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331516410730009, 5.164857103938598e-06, 0.00010166924952414004, 0.3331516410730009, 0.00011830536290759524, 6.143676640929166e-05, 0.3331516410730009, 7.592231362607343e-05, 0.00012518682968980124, 5.739140173644142e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991684341531722, 3.874466233905395e-06, 0.24991684341531722, 0.24991684341531722, 8.874788298128505e-05, 4.608736934689134e-05, 0.24991684341531722, 5.695383911393767e-05, 9.39100801439262e-05, 4.3052700911081244e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.199947396037858, 0.199947396037858, 0.199947396037858, 0.199947396037858, 7.100324997499911e-05, 3.687246271685718e-05, 0.199947396037858, 4.556624383361988e-05, 7.513329525885715e-05, 3.444455892579434e-05]
[1, 1, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.1666397942057945, 0.1666397942057945, 0.1666397942057945, 0.1666397942057945, 0.1666397942057945, 3.0977955226736745e-05, 0.1666397942057945, 3.828417250146988e-05, 6.303924601657623e-05, 2.893339148822875e-05]
[1, 1, 0, 1, 1, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2127]
random_location_list [2127]
Random Combined Rec Success! in episode: 635.
Random Combined Rec Success! in episode: 635.
Rec Success! in episode: 635.
total combined:  61
-----
It has processed 636 episodes
----target item:  1913
[0.9981555808137264, 1.3710723933749225e-05, 0.0002750620029002309, 9.632196078521711e-05, 0.0003190227316431444, 0.00016501604746149898, 0.0002861863847508826, 0.00020345370899961, 0.000335942782054737, 0.00014970284374464198]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 636.
Rec Success! in episode: 636.
total combined:  61
-----
It has processed 637 episodes
----target item:  1114
[2.533908005251207e-05, 1.4563879860641252e-05, 0.00029820972216999337, 0.00010503285938352805, 0.00034968025972671686, 0.000178668678346214, 0.0003106424957466218, 0.9981837819936655, 0.00036528332732922264, 0.00016879770371907497]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.26829486153718e-05, 7.289646645820084e-06, 0.4996200962894889, 5.2572009549130954e-05, 0.00017502516889851097, 8.94288846298022e-05, 0.00015548562943644304, 0.4996200962894889, 0.00018283495931847274, 8.44881739283799e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331672622079263, 4.8610366826474775e-06, 0.3331672622079263, 3.505718168731198e-05, 0.00011671399283668803, 5.963486432130238e-05, 0.00010368422298609952, 0.3331672622079263, 0.00012192188281541445, 5.634019489151126e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990748457594048, 0.24990748457594048, 0.24990748457594048, 2.629625742258607e-05, 8.754671803986484e-05, 4.4731882829061526e-05, 7.777313768750772e-05, 0.24990748457594048, 9.145313632330207e-05, 4.226056393580696e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 637.
Rec Success! in episode: 637.
total combined:  61
-----
It has processed 638 episodes
----target item:  499
[0.9979994749111468, 1.4133018210243557e-05, 0.0002954107988568131, 0.00010098963517988107, 0.0003486151970025175, 0.00017867207319903364, 0.00031101084950430964, 0.00022188955861307782, 0.0003649980891657934, 0.00016480586912115243]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2183]
random_location_list [2183]
Random Combined Rec Success! in episode: 638.
Random Combined Rec Success! in episode: 638.
Rec Success! in episode: 638.
total combined:  62
-----
It has processed 639 episodes
----target item:  1575
[0.9980972601923869, 1.457378482899635e-05, 0.0002813163753816315, 9.79969159770765e-05, 0.00032692650171612297, 0.00017069534504829552, 0.00029424787923721844, 0.00021045789795265683, 0.0003482202836042437, 0.00015830482386689165]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 639.
Rec Success! in episode: 639.
total combined:  62
-----
It has processed 640 episodes
----target item:  898
[0.9979747545055412, 1.4878052774330937e-05, 0.0002996651414791423, 0.00010534478367517273, 0.00034991800913812885, 0.00018129770740270008, 0.0003135058760793802, 0.00022277723233288027, 0.00036861445439433636, 0.00016924423718263468]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9979747545055412, 1.4878052774330937e-05, 0.0002996651414791423, 0.00010534478367517273, 0.00034991800913812885, 0.00018129770740270008, 0.0003135058760793802, 0.00022277723233288027, 0.00036861445439433636, 0.00016924423718263468]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.49951951296179786, 7.446959597025007e-06, 0.00014999235686824011, 0.49951951296179786, 0.00017514558631079034, 9.074552446745731e-05, 0.00015692010426398442, 0.00011150740446238389, 0.0001845037781751977, 8.471236225905078e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331530393923599, 4.966727344184299e-06, 0.3331530393923599, 0.3331530393923599, 0.00011681282292581672, 6.0522455085551885e-05, 0.00010465739239562111, 7.436952861186319e-05, 0.00012305424089237093, 5.649865566486444e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331530393923599, 4.966727344184299e-06, 0.3331530393923599, 0.3331530393923599, 0.00011681282292581672, 6.0522455085551885e-05, 0.00010465739239562111, 7.436952861186319e-05, 0.00012305424089237093, 5.649865566486444e-05]
[-1, 0, 0, -1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331530393923599, 4.966727344184299e-06, 0.3331530393923599, 0.3331530393923599, 0.00011681282292581672, 6.0522455085551885e-05, 0.00010465739239562111, 7.436952861186319e-05, 0.00012305424089237093, 5.649865566486444e-05]
[-1, 0, 0, -1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.3331530393923599, 4.966727344184299e-06, 0.3331530393923599, 0.3331530393923599, 0.00011681282292581672, 6.0522455085551885e-05, 0.00010465739239562111, 7.436952861186319e-05, 0.00012305424089237093, 5.649865566486444e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([6], dtype=torch.int32)
[0.2499181904354683, 3.7258417708236134e-06, 0.2499181904354683, 0.2499181904354683, 8.762834455457887e-05, 4.540154423708945e-05, 0.2499181904354683, 5.578906933616847e-05, 9.231040864979966e-05, 4.238304957851557e-05]
[-1, 0, 0, -1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499181904354683, 3.7258417708236134e-06, 0.2499181904354683, 0.2499181904354683, 8.762834455457887e-05, 4.540154423708945e-05, 0.2499181904354683, 5.578906933616847e-05, 9.231040864979966e-05, 4.238304957851557e-05]
[-1, 0, 0, -1, -1, -1, 0, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.2499181904354683, 3.7258417708236134e-06, 0.2499181904354683, 0.2499181904354683, 8.762834455457887e-05, 4.540154423708945e-05, 0.2499181904354683, 5.578906933616847e-05, 9.231040864979966e-05, 4.238304957851557e-05]
[-1, 0, 0, -1, -1, -1, 0, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  62
-----
It has processed 641 episodes
----target item:  589
[2.7324515348606442e-05, 1.636030949345191e-05, 0.0003052848389394595, 0.00010714714811405444, 0.9982604784496774, 0.0001850554286873359, 0.00032118170054611897, 0.0002289365239667217, 0.00037655042540300104, 0.00017168065982395197]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.3676240306082698e-05, 8.188526722606466e-06, 0.49964107385491674, 5.3628403908506226e-05, 0.49964107385491674, 9.262241179337992e-05, 0.00016075520691015795, 0.0001145854144771804, 0.00018846790288749808, 8.592818316094856e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2190]
random_location_list [2190]
Random Combined Rec Success! in episode: 641.
Random Combined Rec Success! in episode: 641.
Rec Success! in episode: 641.
total combined:  63
-----
It has processed 642 episodes
----target item:  640
[0.9980859736309059, 1.4592476835265827e-05, 0.0002838967842647014, 9.742216244757254e-05, 0.0003290266629611923, 0.00017152112906862298, 0.0002982796027689896, 0.00021199040171982554, 0.00034771646202480023, 0.00015958068700293505]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 642.
Rec Success! in episode: 642.
total combined:  63
-----
It has processed 643 episodes
----target item:  782
[2.3951436991624037e-05, 0.9980394214319379, 0.00028781512121747407, 0.00010194733803298587, 0.00033712319343618714, 0.00017361986688759764, 0.0003019546675000403, 0.00021682023642008035, 0.00035537603112371425, 0.000161970676452446]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 643.
Rec Success! in episode: 643.
total combined:  63
-----
It has processed 644 episodes
----target item:  103
[2.559944611299383e-05, 1.4693603044237106e-05, 0.00029413601031267673, 0.00010152927563586081, 0.0003432600086935501, 0.00017765608117652651, 0.9982981642818177, 0.00021917626328115343, 0.00036116496584267534, 0.00016462006408283169]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([7], dtype=torch.int32)
[1.2812029087188589e-05, 7.353864953461385e-06, 0.0001472094006675716, 5.081344443572063e-05, 0.000171795014487368, 8.891344248242422e-05, 0.4996289787681588, 0.4996289787681588, 0.00018075610023847804, 8.23891673302079e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[8.544304671735313e-06, 4.904270997948431e-06, 0.33320110252418167, 3.388733726129572e-05, 0.00011456959197298827, 5.929611436351742e-05, 0.33320110252418167, 0.33320110252418167, 0.00012054571381332914, 5.4945094374145776e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([0], dtype=torch.int32)
[0.24992721454219227, 3.678591639078848e-06, 0.24992721454219227, 2.5418186632059023e-05, 8.593626724559348e-05, 4.44767816906418e-05, 0.24992721454219227, 0.24992721454219227, 9.041883190101132e-05, 4.121317212235673e-05]
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.19995400306797595, 0.19995400306797595, 0.19995400306797595, 2.0335793271329007e-05, 6.875321951613615e-05, 3.558360204555849e-05, 0.19995400306797595, 0.19995400306797595, 7.233949061711906e-05, 3.2972554669925925e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664427126946452, 0.16664427126946452, 0.16664427126946452, 1.69481150584169e-05, 0.16664427126946452, 2.9655837547842627e-05, 0.16664427126946452, 0.16664427126946452, 6.0288673959660076e-05, 2.7479756646804527e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([3], dtype=torch.int32)
[0.142842763890426, 0.142842763890426, 0.142842763890426, 0.142842763890426, 0.142842763890426, 2.5420146570592195e-05, 0.142842763890426, 0.142842763890426, 5.167774898040917e-05, 2.3554871467010475e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 644.
Rec Success! in episode: 644.
total combined:  63
-----
It has processed 645 episodes
----target item:  991
[0.9981065753733318, 1.4445319997045365e-05, 0.00027962589860266936, 9.693929829399514e-05, 0.0003273180240774727, 0.00016914570506665246, 0.00029477129756222105, 0.0002097039152927862, 0.00034601851629909204, 0.00015545665147611155]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 645.
Rec Success! in episode: 645.
total combined:  63
-----
It has processed 646 episodes
----target item:  24
[2.519692478177109e-05, 1.4628447446792016e-05, 0.00029313420645513973, 0.00010135896049849713, 0.9983417021339445, 0.00017630312524171988, 0.00030533862213013923, 0.00021871872526482174, 0.0003593034075355307, 0.00016431544670115662]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.2610766918397304e-05, 7.321367298876838e-06, 0.49965837575684746, 5.072897732592831e-05, 0.49965837575684746, 8.823765751830215e-05, 0.00015281841844658312, 0.00010946617053042486, 0.00017982716401544955, 8.223796425108709e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 646.
Rec Success! in episode: 646.
total combined:  63
-----
It has processed 647 episodes
----target item:  906
[0.9981468420127019, 1.3891291145540534e-05, 0.0002742301573750595, 9.465315883596955e-05, 0.00031969307285628304, 0.0001677647708877073, 0.00028776554068960056, 0.0002034699868085947, 0.000337158118678069, 0.00015453189002139227]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 647.
Rec Success! in episode: 647.
total combined:  63
-----
It has processed 648 episodes
----target item:  1885
[2.2855454305167345e-05, 0.9981271965969489, 0.00027685577919096555, 9.613348791034477e-05, 0.0003219569798274486, 0.0001664485566634155, 0.00028977290304066323, 0.00020626590709299893, 0.0003379868599166861, 0.00015452747510303122]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 648.
Rec Success! in episode: 648.
total combined:  63
-----
It has processed 649 episodes
----target item:  1885
[2.2399192974098256e-05, 0.9981605091978409, 0.00027180790326608036, 9.440875071847941e-05, 0.0003155606233550932, 0.00016327789469533713, 0.0002850881941573104, 0.0002031596319365134, 0.00033219194476875874, 0.00015159666628715285]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 649.
Rec Success! in episode: 649.
total combined:  63
-----
It has processed 650 episodes
----target item:  1813
[0.9980621379965924, 1.4141883947436229e-05, 0.0002876888788758527, 0.00010033805350285753, 0.00033460752104282667, 0.00017319639431625703, 0.00029974517218497225, 0.00021392896826006376, 0.00035184280963419925, 0.0001623723216433335]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 650.
Rec Success! in episode: 650.
total combined:  63
-----
It has processed 651 episodes
----target item:  1588
[2.6044467769091856e-05, 1.4899392366906624e-05, 0.00029483156468134146, 0.00010173789406959561, 0.9983286952465273, 0.0001793824542272286, 0.00030665493477221087, 0.00021990363683688387, 0.0003620187657547879, 0.00016583164299445167]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.3035048225408364e-05, 7.457026949208459e-06, 0.49965554307817023, 5.091900388621027e-05, 0.49965554307817023, 8.977948646809939e-05, 0.0001534783470622101, 0.00011006001491469212, 0.00018118750254196567, 8.29974136118334e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 651.
Rec Success! in episode: 651.
total combined:  63
-----
It has processed 652 episodes
----target item:  1187
[0.9979582440836883, 1.5117376749765316e-05, 0.00030068538432272455, 0.00010541981124916851, 0.00035227315605554805, 0.00018270915131521966, 0.0003170212913280614, 0.00022636633029564417, 0.00037186655316038327, 0.00017029686183512856]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 652.
Rec Success! in episode: 652.
total combined:  63
-----
It has processed 653 episodes
----target item:  578
[0.9980377241518263, 1.5055758344527977e-05, 0.000291282349019219, 0.00010272476726962372, 0.0003392887332603657, 0.00017452763242761313, 0.00030312147231690884, 0.00021657094402817423, 0.00035670039085339847, 0.00016300380065382443]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 653.
Rec Success! in episode: 653.
total combined:  63
-----
It has processed 654 episodes
----target item:  548
[2.5477793788478325e-05, 1.4753882872583358e-05, 0.00030535104470914495, 0.00010768762569796509, 0.0003569267916705783, 0.9980965286705017, 0.0003179882786685312, 0.00022693843482783142, 0.000376326032141343, 0.00017202144512196867]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[1.275306210040741e-05, 7.385144336213368e-06, 0.00015284529217600619, 5.3903685278771603e-05, 0.00017866184086679228, 0.4996031884869183, 0.4996031884869183, 0.00011359539120052864, 0.00018837224673938708, 8.610636346520637e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[8.505158012259094e-06, 4.925234349860839e-06, 0.3331908860832692, 3.594896324737499e-05, 0.0001191515555534395, 0.3331908860832692, 0.3331908860832692, 7.575802140836574e-05, 0.0001256275325117066, 5.742528510930704e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[5.888840095474735e-06, 0.24992091079334047, 0.24992091079334047, 2.696471605953516e-05, 8.93735889249889e-05, 0.24992091079334047, 0.24992091079334047, 5.6824824750903873e-05, 9.423111092600278e-05, 4.307374588120802e-05]
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 654.
Rec Success! in episode: 654.
total combined:  63
-----
It has processed 655 episodes
----target item:  1566
[0.9980897401191459, 1.462765866165071e-05, 0.00028315016183277653, 9.900287728258148e-05, 0.0003303723827426604, 0.000170074375753466, 0.00029460657754468004, 0.0002106026120137517, 0.0003473846530093854, 0.00016043858201302742]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 655.
Rec Success! in episode: 655.
total combined:  63
-----
It has processed 656 episodes
----target item:  1652
[0.9980377381803345, 1.535684442534222e-05, 0.0002894036028524776, 0.00010079731333543566, 0.00033641089380088675, 0.00017558293961155412, 0.00030434467935011583, 0.00021904175956459615, 0.0003573502325379931, 0.00016397355418707263]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 656.
Rec Success! in episode: 656.
total combined:  63
-----
It has processed 657 episodes
----target item:  854
[2.2774217594456602e-05, 0.9981026313162447, 0.0002770451039403951, 9.74646913795717e-05, 0.00032850191118363617, 0.000168588685277184, 0.00029176602011616313, 0.00020990051700642466, 0.00034309780671109755, 0.00015822973054611212]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 657.
Rec Success! in episode: 657.
total combined:  63
-----
It has processed 658 episodes
----target item:  603
[2.486793415618651e-05, 1.480661178386809e-05, 0.00028689994502975537, 9.962280914039277e-05, 0.9983662725186685, 0.00017379757696522893, 0.00030217330461287847, 0.0002158237035970537, 0.00035360665285488394, 0.00016212894319132806]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2445919064844359e-05, 7.410422222014303e-06, 0.499662969460876, 4.9859285125431706e-05, 0.499662969460876, 8.698231879615865e-05, 0.0001512318823569367, 0.00010801558064185437, 0.0001769732762915312, 8.114239374910158e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 658.
Rec Success! in episode: 658.
total combined:  63
-----
It has processed 659 episodes
----target item:  805
[2.339121910259784e-05, 0.9980122284751654, 0.0002946068674106295, 0.0001030479980935285, 0.00034203913613597823, 0.00017614753377571406, 0.0003058692639365338, 0.0002187248476948646, 0.0003583545797946081, 0.00016559007889035743]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 659.
Rec Success! in episode: 659.
total combined:  63
-----
It has processed 660 episodes
----target item:  1214
[0.9980344827135864, 1.46822758728482e-05, 0.000290572012961482, 0.00010086666989435085, 0.0003395044241268134, 0.0001760109759542598, 0.00030657225798834907, 0.0002165473294644289, 0.0003575754321082614, 0.00016318590804289182]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 660.
Rec Success! in episode: 660.
total combined:  63
-----
It has processed 661 episodes
----target item:  1573
[2.5464253186415757e-05, 1.5230553195696174e-05, 0.00028503398052465834, 9.93889766023112e-05, 0.9983694875108617, 0.00017284696941824966, 0.0003020563781099137, 0.00021462145022662366, 0.0003534392120281048, 0.0001624307158462863]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[1.2744332774034637e-05, 7.622577298364897e-06, 0.4996633078981632, 4.9742129981895783e-05, 0.4996633078981632, 8.650633816446206e-05, 0.00015117297848758204, 0.00010741360298730993, 0.00017688902558829633, 8.129321839189224e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 661.
Rec Success! in episode: 661.
total combined:  63
-----
It has processed 662 episodes
----target item:  2065
[2.2535202291684557e-05, 0.9980953253499047, 0.00027956084887917717, 9.698988473953256e-05, 0.0003267790098864953, 0.00016923505453816384, 0.00029579962585051477, 0.00021148586362595842, 0.0003449521524356986, 0.0001573370078478778]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 662.
Rec Success! in episode: 662.
total combined:  63
-----
It has processed 663 episodes
----target item:  2065
[0.9980746598457695, 1.4952242227258622e-05, 0.0002842377236444585, 9.8643463087767e-05, 0.0003317279213848028, 0.00017144276578675088, 0.0002995820076169758, 0.00021484162313474138, 0.00035024699358141486, 0.000159665413766248]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 663.
Rec Success! in episode: 663.
total combined:  63
-----
It has processed 664 episodes
----target item:  2065
[2.4402683551942202e-05, 1.473414583881583e-05, 0.00028998874645181353, 0.00010062639596427583, 0.9983501648775376, 0.00017582049001635324, 0.0003047631763602468, 0.00021840746051310253, 0.00035742164711254494, 0.00016367037665329916]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2213187492277625e-05, 7.374225268503212e-06, 0.49965970835306783, 5.036204473036557e-05, 0.49965970835306783, 8.799559298399143e-05, 0.00015252952839006607, 0.00010930975108868473, 0.00017888432559855786, 8.191463831195509e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 664.
Rec Success! in episode: 664.
total combined:  63
-----
It has processed 665 episodes
----target item:  2065
[2.2535202291684557e-05, 0.9980953253499047, 0.00027956084887917717, 9.698988473953256e-05, 0.0003267790098864953, 0.00016923505453816384, 0.00029579962585051477, 0.00021148586362595842, 0.0003449521524356986, 0.0001573370078478778]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 665.
Rec Success! in episode: 665.
total combined:  63
-----
It has processed 666 episodes
----target item:  2065
[0.9981031550750653, 1.4690712374516156e-05, 0.00027956304194085853, 9.699064559285144e-05, 0.0003267815733589119, 0.00016923638213076037, 0.00029580194629998905, 0.00021148752266206996, 0.0003449548584703613, 0.00015733824210426367]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 666.
Rec Success! in episode: 666.
total combined:  63
-----
It has processed 667 episodes
----target item:  2065
[2.4072061906401537e-05, 1.4524917416474345e-05, 0.000284055385518607, 9.854452192653901e-05, 0.9983818934784989, 0.00017237048091518572, 0.00029967311148519117, 0.00021470313044707817, 0.0003502014884965293, 0.0001599614233888711]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2047489090612469e-05, 7.269372469937299e-06, 0.49966616971638, 4.931916748410661e-05, 0.49966616971638, 8.62672876317704e-05, 0.00014997919810133244, 0.00010745376245038863, 0.00017526743777009828, 8.005685224180068e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 667.
Rec Success! in episode: 667.
total combined:  63
-----
It has processed 668 episodes
----target item:  2065
[2.2797447227373965e-05, 0.9980668296283782, 0.00028423549370790516, 9.864268919800576e-05, 0.00033172531887234183, 0.00017144142076299637, 0.00029957965729956917, 0.00021483993763296328, 0.00035024424578086375, 0.000159664161139616]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 668.
Rec Success! in episode: 668.
total combined:  63
-----
It has processed 669 episodes
----target item:  2065
[2.4072061906401537e-05, 1.4524917416474345e-05, 0.000284055385518607, 9.854452192653901e-05, 0.9983818934784989, 0.00017237048091518572, 0.00029967311148519117, 0.00021470313044707817, 0.0003502014884965293, 0.0001599614233888711]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2047489090612469e-05, 7.269372469937299e-06, 0.49966616971638, 4.931916748410661e-05, 0.49966616971638, 8.62672876317704e-05, 0.00014997919810133244, 0.00010745376245038863, 0.00017526743777009828, 8.005685224180068e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 669.
Rec Success! in episode: 669.
total combined:  63
-----
It has processed 670 episodes
----target item:  2065
[2.2535202291684557e-05, 0.9980953253499047, 0.00027956084887917717, 9.698988473953256e-05, 0.0003267790098864953, 0.00016923505453816384, 0.00029579962585051477, 0.00021148586362595842, 0.0003449521524356986, 0.0001573370078478778]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 670.
Rec Success! in episode: 670.
total combined:  63
-----
It has processed 671 episodes
----target item:  459
[0.9981642352971076, 1.3982941672487233e-05, 0.00027014704970401937, 9.512409295516099e-05, 0.00031809530518290175, 0.00016351723304482724, 0.0002838323656651512, 0.00020327126222548908, 0.000334034123468813, 0.00015376032897345177]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 671.
Rec Success! in episode: 671.
total combined:  63
-----
It has processed 672 episodes
----target item:  32
[2.6053270022872656e-05, 1.5198088542112164e-05, 0.00031131031629986957, 0.00010877287373890559, 0.9982392250101655, 0.0001880218495135323, 0.00032503569220588283, 0.00022961235350332164, 0.00038303079914108623, 0.00017373974686688614]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 1, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2690833248323915e-05, 7.4437377107501605e-06, 0.49964882003297556, 5.2657545146650255e-05, 0.49964882003297556, 9.108552833125358e-05, 0.00015750784493757364, 0.00011123209778708367, 0.00018558150577263478, 8.41608411144512e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331800363462905, 4.963695903167171e-06, 0.3331800363462905, 3.511354796096482e-05, 0.3331800363462905, 6.073841951237924e-05, 0.00010503070836365276, 7.417272471718995e-05, 0.00012375102343771175, 5.612084123324182e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991469101197628, 0.24991469101197628, 0.24991469101197628, 2.63382872072144e-05, 0.24991469101197628, 4.5559222309512326e-05, 7.87823823879702e-05, 5.5636147298893474e-05, 9.282428540438538e-05, 4.2095627486997715e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2119]
random_location_list [2119]
Random Combined Rec Success! in episode: 672.
Random Combined Rec Success! in episode: 672.
Rec Success! in episode: 672.
total combined:  64
-----
It has processed 673 episodes
----target item:  1428
[0.9980834845440714, 1.3973109565161616e-05, 0.00028492608305308737, 9.908612805925642e-05, 0.0003322889084856211, 0.0001701257701488331, 0.000295925540600636, 0.00021124735112238629, 0.00034991406132776676, 0.0001590285035657881]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 673.
Rec Success! in episode: 673.
total combined:  64
-----
It has processed 674 episodes
----target item:  1428
[0.9980834845440714, 1.3973109565161616e-05, 0.00028492608305308737, 9.908612805925642e-05, 0.0003322889084856211, 0.0001701257701488331, 0.000295925540600636, 0.00021124735112238629, 0.00034991406132776676, 0.0001590285035657881]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 674.
Rec Success! in episode: 674.
total combined:  64
-----
It has processed 675 episodes
----target item:  103
[0.9981088535018301, 1.4525480090092078e-05, 0.00027982727278388713, 9.760502000794254e-05, 0.0003269703320669747, 0.00016879143767935327, 0.00029325612974630543, 0.00021048857227520582, 0.0003435614125410091, 0.00015612084097913774]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 675.
Rec Success! in episode: 675.
total combined:  64
-----
It has processed 676 episodes
----target item:  1061
[2.465969706124553e-05, 1.446650229922231e-05, 0.000286719155437669, 0.00010027640207441154, 0.0003362433328893684, 0.00017234800267700178, 0.00030171803999247984, 0.9982508314498909, 0.0003513682086619635, 0.00016136920901581054]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2342412413467446e-05, 7.240621695956811e-06, 0.49963401509925215, 5.018929091737015e-05, 0.00016829297924837497, 8.626181101875651e-05, 0.0001510127424891472, 0.49963401509925215, 0.00017586312311608726, 8.076682059643946e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331733757915548, 4.828298915541779e-06, 0.3331733757915548, 3.34679685093155e-05, 0.00011222362434042994, 5.752238220470844e-05, 0.00010070056017434118, 0.3331733757915548, 0.00011727166012544832, 5.3858131065638274e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991091817922925, 0.24991091817922925, 0.24991091817922925, 2.5104078979556248e-05, 8.417812177724629e-05, 4.314711917926195e-05, 7.553475542438656e-05, 0.24991091817922925, 8.796461658655791e-05, 4.039859113608112e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 676.
Rec Success! in episode: 676.
total combined:  64
-----
It has processed 677 episodes
----target item:  814
[2.576134412604265e-05, 1.5054003549839498e-05, 0.00029867347484550656, 0.00010430792258791461, 0.0003468182094765685, 0.00017955289514461374, 0.9982759401806661, 0.00022175356168910657, 0.0003651757711600214, 0.00016696263675440852]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([7], dtype=torch.int32)
[1.2893215959090132e-05, 7.534331976908618e-06, 0.00014948216962569429, 5.220475164611029e-05, 0.00017357797991627026, 8.986387673922175e-05, 0.4996240576787892, 0.4996240576787892, 0.00018276569955190074, 8.35626170063664e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([2], dtype=torch.int32)
[8.598489210603716e-06, 5.024648033362119e-06, 0.3331994192093161, 3.4815362993656344e-05, 0.00011575920175727545, 5.993024370467065e-05, 0.3331994192093161, 0.3331994192093161, 0.00012188649446746408, 5.5727931884401415e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 1, 0]
action is: tensor([0], dtype=torch.int32)
[0.24992627764219297, 3.7688888606719646e-06, 0.24992627764219297, 2.611431345953259e-05, 8.682868195473298e-05, 4.495248750085162e-05, 0.24992627764219297, 0.24992627764219297, 9.14246427241591e-05, 4.1800416728267535e-05]
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.1999534178254526, 0.1999534178254526, 0.1999534178254526, 2.089274597157139e-05, 6.946725204695734e-05, 3.5964219530446776e-05, 0.1999534178254526, 0.1999534178254526, 7.31442486105364e-05, 3.3442406577635846e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664396396826375, 0.16664396396826375, 0.16664396396826375, 1.7412305549705097e-05, 0.16664396396826375, 2.997308157448063e-05, 0.16664396396826375, 0.16664396396826375, 6.095943576508538e-05, 2.7871367528213244e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([3], dtype=torch.int32)
[0.14284259494244958, 0.14284259494244958, 0.14284259494244958, 0.14284259494244958, 0.14284259494244958, 2.5692096182589044e-05, 0.14284259494244958, 0.14284259494244958, 5.2252741614875834e-05, 2.389056505570705e-05]
[0, 0, 1, 1, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 677.
Rec Success! in episode: 677.
total combined:  64
-----
It has processed 678 episodes
----target item:  1154
[2.630324090152338e-05, 1.5206636005343786e-05, 0.00030617626358515887, 0.00010728407451545144, 0.0003578787675324529, 0.9980885872075268, 0.0003215210064371209, 0.00022889201760366296, 0.0003772810083587294, 0.00017086977753393812]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 678.
Rec Success! in episode: 678.
total combined:  64
-----
It has processed 679 episodes
----target item:  1789
[0.9981076426484331, 1.4425002828350982e-05, 0.0002799384380394522, 9.764195652328405e-05, 0.000326469116000194, 0.00016724685164207475, 0.00029557034016056306, 0.00020844945298171907, 0.0003437906954886544, 0.00015882549790264338]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 679.
Rec Success! in episode: 679.
total combined:  64
-----
It has processed 680 episodes
----target item:  1811
[2.4260426689820895e-05, 1.4321556337935676e-05, 0.0002863800197974437, 0.00010048904219744857, 0.00033452527962355284, 0.9982084383794095, 0.00030101711878276156, 0.0002162938533629737, 0.00035217382706274474, 0.00016210049673576023]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 680.
Rec Success! in episode: 680.
total combined:  64
-----
It has processed 681 episodes
----target item:  1789
[0.9980552867856415, 1.4045561298641194e-05, 0.0002859226382429144, 0.00010163137720149006, 0.0003371691272355867, 0.00017377131467282512, 0.0003023108249695676, 0.00021360359550013722, 0.0003550586871516991, 0.00016120008808563955]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 681.
Rec Success! in episode: 681.
total combined:  64
-----
It has processed 682 episodes
----target item:  2070
[0.9979544501538918, 1.5299062782382443e-05, 0.0003026222494257565, 0.00010711471559604805, 0.0003540488749931203, 0.00018131354272834523, 0.000315741867028399, 0.00022689969932899266, 0.00037259027119038716, 0.0001699195630346713]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 682.
Rec Success! in episode: 682.
total combined:  64
-----
It has processed 683 episodes
----target item:  2070
[2.254145600277061e-05, 0.9979734720341087, 0.00029890684370751215, 0.00010543644378327715, 0.00034978352704800837, 0.0001790038041926968, 0.00031127045745150684, 0.00022384904224854597, 0.000368104282244941, 0.00016763210921216592]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.254145600277061e-05, 0.9979734720341087, 0.00029890684370751215, 0.00010543644378327715, 0.00034978352704800837, 0.0001790038041926968, 0.00031127045745150684, 0.00022384904224854597, 0.000368104282244941, 0.00016763210921216592]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1282755217668878e-05, 0.49951921461080384, 0.00014961290654975213, 0.49951921461080384, 0.00017507839397643457, 8.959741134243894e-05, 0.00015580131014986354, 0.0001120439579896495, 0.00018424854679462073, 8.390549637210368e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.895149477360048e-06, 0.33314281332507595, 0.33314281332507595, 0.33314281332507595, 0.00012313353124867514, 6.310532952788224e-05, 0.00010967920436453908, 7.892825971731066e-05, 0.00012960752994998373, 5.9211020486286834e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 683.
Rec Success! in episode: 683.
total combined:  64
-----
It has processed 684 episodes
----target item:  2070
[2.226474362282091e-05, 0.9979984580184268, 0.00029478347474398573, 0.00010406601227330507, 0.0003452372435843924, 0.0001770481928028822, 0.0003078783539342088, 0.00022179184454268618, 0.00036316850555211545, 0.00016530361051687243]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.226474362282091e-05, 0.9979984580184268, 0.00029478347474398573, 0.00010406601227330507, 0.0003452372435843924, 0.0001770481928028822, 0.0003078783539342088, 0.00022179184454268618, 0.00036316850555211545, 0.00016530361051687243]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1144104369032302e-05, 0.499525131063761, 0.00014754707552283767, 0.499525131063761, 0.00017280054689864163, 8.861739314714335e-05, 0.0001541014155533305, 0.00011101279698772141, 0.00018177562688258297, 8.273891311686675e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.709143640321544e-06, 0.3331459720634045, 0.3331459720634045, 0.3331459720634045, 0.0001210737142550356, 6.210422493371613e-05, 0.00010799014859710631, 7.77316848670384e-05, 0.00012742404791528264, 5.805084557772771e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 684.
Rec Success! in episode: 684.
total combined:  64
-----
It has processed 685 episodes
----target item:  2070
[2.5425962482293458e-05, 1.5173377259209627e-05, 0.998200515897506, 0.00010903574808126816, 0.0003602539458021937, 0.000184518587242795, 0.00032144824035967916, 0.00023140107319246733, 0.0003789842944565526, 0.00017324287361719166]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 685.
Rec Success! in episode: 685.
total combined:  64
-----
It has processed 686 episodes
----target item:  2070
[2.2619043299989274e-05, 0.9979914092265182, 0.0002955750507552308, 0.00010463440181681103, 0.00034576556027751215, 0.00017731804401290182, 0.0003093800126620337, 0.00022234828061592447, 0.0003644165515491854, 0.00016653382849232524]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2619043299989274e-05, 0.9979914092265182, 0.0002955750507552308, 0.00010463440181681103, 0.00034576556027751215, 0.00017731804401290182, 0.0003093800126620337, 0.00022234828061592447, 0.0003644165515491854, 0.00016653382849232524]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1321484072576591e-05, 0.4995235074390459, 0.0001479438447061972, 0.4995235074390459, 0.0001730656434761426, 8.875279933141358e-05, 0.00015485362662214893, 0.00011129173255347954, 0.000182401002970331, 8.335498817591264e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.857675619200262e-06, 0.33314488590663566, 0.33314488590663566, 0.33314488590663566, 0.00012156621748253081, 6.233183991428334e-05, 0.00010868831750703378, 7.823723757604024e-05, 0.00012803332126752818, 5.8627670726454445e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 686.
Rec Success! in episode: 686.
total combined:  64
-----
It has processed 687 episodes
----target item:  2070
[2.5505354176535492e-05, 1.523324068669578e-05, 0.9981787199321795, 0.00011018934564994582, 0.0003642403545336626, 0.00018676053215505056, 0.00032565520357757456, 0.00023441676267114552, 0.0003836172852651952, 0.00017566198910445882]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 687.
Rec Success! in episode: 687.
total combined:  64
-----
It has processed 688 episodes
----target item:  2070
[0.9980089584549473, 1.4435660759459682e-05, 0.0002951028649062303, 0.00010395017478345935, 0.0003450304248342545, 0.00017671995267381002, 0.00030683170330536114, 0.00022072912773078251, 0.00036311663416379854, 0.0001651250018955221]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 688.
Rec Success! in episode: 688.
total combined:  64
-----
It has processed 689 episodes
----target item:  2070
[2.226474362282091e-05, 0.9979984580184268, 0.00029478347474398573, 0.00010406601227330507, 0.0003452372435843924, 0.0001770481928028822, 0.0003078783539342088, 0.00022179184454268618, 0.00036316850555211545, 0.00016530361051687243]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.226474362282091e-05, 0.9979984580184268, 0.00029478347474398573, 0.00010406601227330507, 0.0003452372435843924, 0.0001770481928028822, 0.0003078783539342088, 0.00022179184454268618, 0.00036316850555211545, 0.00016530361051687243]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1144104369032302e-05, 0.499525131063761, 0.00014754707552283767, 0.499525131063761, 0.00017280054689864163, 8.861739314714335e-05, 0.0001541014155533305, 0.00011101279698772141, 0.00018177562688258297, 8.273891311686675e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.709143640321544e-06, 0.3331459720634045, 0.3331459720634045, 0.3331459720634045, 0.0001210737142550356, 6.210422493371613e-05, 0.00010799014859710631, 7.77316848670384e-05, 0.00012742404791528264, 5.805084557772771e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 689.
Rec Success! in episode: 689.
total combined:  64
-----
It has processed 690 episodes
----target item:  2070
[2.5126290216956654e-05, 1.4950774829973277e-05, 0.9981954816784474, 0.00010914595115957362, 0.0003615516269138005, 0.00018523166250446443, 0.0003223711291387975, 0.00023196098749893906, 0.0003804636226076752, 0.00017371627668242003]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 690.
Rec Success! in episode: 690.
total combined:  64
-----
It has processed 691 episodes
----target item:  2070
[2.5126205815795823e-05, 1.4955443741388186e-05, 0.9982075713542309, 0.00010823235319594362, 0.0003585823938253964, 0.00018393607856418006, 0.0003203728609202423, 0.0002308759729844026, 0.0003776772870417696, 0.00017267004968006327]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 691.
Rec Success! in episode: 691.
total combined:  64
-----
It has processed 692 episodes
----target item:  2070
[2.532922653479748e-05, 1.5112248169894559e-05, 0.9982018782494498, 0.00010877830345478595, 0.00035997711807963563, 0.00018475685614753086, 0.0003209111483468479, 0.00023080771987125554, 0.0003792576976859392, 0.00017319143225933708]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 692.
Rec Success! in episode: 692.
total combined:  64
-----
It has processed 693 episodes
----target item:  2070
[0.9979544501538918, 1.5299062782382443e-05, 0.0003026222494257565, 0.00010711471559604805, 0.0003540488749931203, 0.00018131354272834523, 0.000315741867028399, 0.00022689969932899266, 0.00037259027119038716, 0.0001699195630346713]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 693.
Rec Success! in episode: 693.
total combined:  64
-----
It has processed 694 episodes
----target item:  2070
[2.2307791404829452e-05, 0.9980011018846263, 0.00029510054178438815, 0.00010394935646228984, 0.0003450277086704639, 0.0001767185614911723, 0.0003068292878512379, 0.00022072739009716788, 0.00036311377562094993, 0.0001651237019911694]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2307791404829452e-05, 0.9980011018846263, 0.00029510054178438815, 0.00010394935646228984, 0.0003450277086704639, 0.0001767185614911723, 0.0003068292878512379, 0.00022072739009716788, 0.00036311377562094993, 0.0001651237019911694]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1165635516623515e-05, 0.4995257641874825, 0.00014770557203656068, 0.4995257641874825, 0.0001726954304098495, 8.84522815739291e-05, 0.00015357611750082948, 0.00011047985619172475, 0.0001817479819526552, 8.264874985292403e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.824892199258333e-06, 0.33314627108903777, 0.33314627108903777, 0.33314627108903777, 0.00012086014729130177, 6.202738958230924e-05, 0.00010774033244794888, 7.747456139101883e-05, 0.00012728598434786674, 5.797342562709112e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 694.
Rec Success! in episode: 694.
total combined:  64
-----
It has processed 695 episodes
----target item:  2070
[2.482172420147479e-05, 1.4737017849535755e-05, 0.9982075076775762, 0.00010842012816057438, 0.00035925995234121144, 0.00018409335862499822, 0.00032018193072991, 0.00023048113762961494, 0.00037797520075233095, 0.00017252187213416732]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 695.
Rec Success! in episode: 695.
total combined:  64
-----
It has processed 696 episodes
----target item:  2070
[2.486992834435922e-05, 1.4858036800836291e-05, 0.998242255873575, 0.00010596379669537947, 0.00035155137380632, 0.00018053034571924485, 0.0003142972984330744, 0.00022610763081527005, 0.00037049526362761115, 0.00016907045218292831]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 696.
Rec Success! in episode: 696.
total combined:  64
-----
It has processed 697 episodes
----target item:  2070
[2.2619043299989274e-05, 0.9979914092265182, 0.0002955750507552308, 0.00010463440181681103, 0.00034576556027751215, 0.00017731804401290182, 0.0003093800126620337, 0.00022234828061592447, 0.0003644165515491854, 0.00016653382849232524]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2619043299989274e-05, 0.9979914092265182, 0.0002955750507552308, 0.00010463440181681103, 0.00034576556027751215, 0.00017731804401290182, 0.0003093800126620337, 0.00022234828061592447, 0.0003644165515491854, 0.00016653382849232524]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1321484072576591e-05, 0.4995235074390459, 0.0001479438447061972, 0.4995235074390459, 0.0001730656434761426, 8.875279933141358e-05, 0.00015485362662214893, 0.00011129173255347954, 0.000182401002970331, 8.335498817591264e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.857675619200262e-06, 0.33314488590663566, 0.33314488590663566, 0.33314488590663566, 0.00012156621748253081, 6.233183991428334e-05, 0.00010868831750703378, 7.823723757604024e-05, 0.00012803332126752818, 5.8627670726454445e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 697.
Rec Success! in episode: 697.
total combined:  64
-----
It has processed 698 episodes
----target item:  2070
[0.9979275355318605, 1.4882627346476407e-05, 0.00030705356794580915, 0.00010836177310865042, 0.00035891938827444767, 0.00018354820174063316, 0.0003198012344877343, 0.00022987146968788866, 0.0003776740357535681, 0.00017235216979441067]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 698.
Rec Success! in episode: 698.
total combined:  64
-----
It has processed 699 episodes
----target item:  2070
[2.254145600277061e-05, 0.9979734720341087, 0.00029890684370751215, 0.00010543644378327715, 0.00034978352704800837, 0.0001790038041926968, 0.00031127045745150684, 0.00022384904224854597, 0.000368104282244941, 0.00016763210921216592]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.254145600277061e-05, 0.9979734720341087, 0.00029890684370751215, 0.00010543644378327715, 0.00034978352704800837, 0.0001790038041926968, 0.00031127045745150684, 0.00022384904224854597, 0.000368104282244941, 0.00016763210921216592]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1282755217668878e-05, 0.49951921461080384, 0.00014961290654975213, 0.49951921461080384, 0.00017507839397643457, 8.959741134243894e-05, 0.00015580131014986354, 0.0001120439579896495, 0.00018424854679462073, 8.390549637210368e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.895149477360048e-06, 0.33314281332507595, 0.33314281332507595, 0.33314281332507595, 0.00012313353124867514, 6.310532952788224e-05, 0.00010967920436453908, 7.892825971731066e-05, 0.00012960752994998373, 5.9211020486286834e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 699.
Rec Success! in episode: 699.
total combined:  64
-----
It has processed 700 episodes
----target item:  2070
[2.3103225499037614e-05, 0.997919331848513, 0.00030705104374424897, 0.00010836088229680097, 0.00035891643769847515, 0.00018354669284216863, 0.00031979860549117043, 0.00022986957997878576, 0.00037767093100088064, 0.00017235075293539547]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3103225499037614e-05, 0.997919331848513, 0.00030705104374424897, 0.00010836088229680097, 0.00035891643769847515, 0.00018354669284216863, 0.00031979860549117043, 0.00022986957997878576, 0.00037767093100088064, 0.00017235075293539547]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1564270010923017e-05, 0.49950638291163335, 0.0001536937419037936, 0.49950638291163335, 0.0001796548536946364, 9.187390374245394e-05, 0.00016007450661686165, 0.00011506072562391234, 0.00018904237512432158, 8.626980001618479e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[8.091910422378809e-06, 0.33313764178135646, 0.33313764178135646, 0.33313764178135646, 0.00012649595036129098, 6.47616752225672e-05, 0.00011275729590510985, 8.106015905096115e-05, 0.00013307440067870696, 6.083326428963709e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 700.
Rec Success! in episode: 700.
total combined:  64
-----
It has processed 701 episodes
----target item:  2070
[2.2174355658358482e-05, 0.9980160258825128, 0.00029185875175153237, 0.00010319565809619447, 0.0003418261506094666, 0.00017527626269467377, 0.0003052534281173246, 0.00022013352904877903, 0.0003600656161843298, 0.00016419036532639683]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2174355658358482e-05, 0.9980160258825128, 0.00029185875175153237, 0.00010319565809619447, 0.0003418261506094666, 0.00017527626269467377, 0.0003052534281173246, 0.00022013352904877903, 0.0003600656161843298, 0.00016419036532639683]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1098760327730485e-05, 0.4995293141845485, 0.0001460818246603628, 0.4995293141845485, 0.0001710916239379027, 8.772968472052198e-05, 0.00015278615938566094, 0.00011018174853206807, 0.00018022088388304977, 8.218094545594069e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.740712875511953e-06, 0.33314784749902304, 0.33314784749902304, 0.33314784749902304, 0.00011967546238094506, 6.138794215709496e-05, 0.00010692318118553631, 7.705394714112164e-05, 0.00012604830782493234, 5.762794936570246e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 701.
Rec Success! in episode: 701.
total combined:  64
-----
It has processed 702 episodes
----target item:  2070
[0.9979011255111084, 1.5112694612967927e-05, 0.0003107008981252619, 0.00010966491292938558, 0.00036336839442452536, 0.00018627339396541244, 0.000324165027159712, 0.0002328564390019125, 0.0003823423547613511, 0.00017439037391106887]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 702.
Rec Success! in episode: 702.
total combined:  64
-----
It has processed 703 episodes
----target item:  2070
[0.9979011255111084, 1.5112694612967927e-05, 0.0003107008981252619, 0.00010966491292938558, 0.00036336839442452536, 0.00018627339396541244, 0.000324165027159712, 0.0002328564390019125, 0.0003823423547613511, 0.00017439037391106887]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 703.
Rec Success! in episode: 703.
total combined:  64
-----
It has processed 704 episodes
----target item:  2070
[2.661847534118068e-05, 1.5753086546991053e-05, 0.9980832737245418, 0.00011604535811684718, 0.0003840328938485883, 0.00019686679773776224, 0.00034245958886497483, 0.0002461118214010232, 0.00040412577270686456, 0.00018471248089392504]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 704.
Rec Success! in episode: 704.
total combined:  64
-----
It has processed 705 episodes
----target item:  2070
[2.5995838066950575e-05, 1.542222119334334e-05, 0.9981615911671052, 0.00011132243709367727, 0.00036824351412926637, 0.0001885602794522664, 0.00032840599798765447, 0.00023602929244158558, 0.00038745126875168706, 0.00017697798377817482]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 705.
Rec Success! in episode: 705.
total combined:  64
-----
It has processed 706 episodes
----target item:  1811
[2.526020388868244e-05, 1.5281000385747364e-05, 0.00029194791866296577, 0.00010185914306659227, 0.00034419198796040217, 0.9981720340589234, 0.00030590132373349544, 0.00021997533710369817, 0.0003602232408900692, 0.00016332578538512805]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 706.
Rec Success! in episode: 706.
total combined:  64
-----
It has processed 707 episodes
----target item:  1290
[2.2399608856200852e-05, 0.9980827075256975, 0.00028461797989808686, 9.8569361800056e-05, 0.00032826614925928133, 0.00017040908379864232, 0.00029416926342006543, 0.00021187668311403537, 0.00034810215431929235, 0.00015888218983663155]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2399608856200852e-05, 0.9980827075256975, 0.00028461797989808686, 9.8569361800056e-05, 0.00032826614925928133, 0.00017040908379864232, 0.00029416926342006543, 0.00021187668311403537, 0.00034810215431929235, 0.00015888218983663155]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.121110444689796e-05, 0.4995448604726729, 0.00014245257230102162, 0.4995448604726729, 0.00016429867634532404, 8.529050884019753e-05, 0.00014723303243558303, 0.00010604522782085015, 0.0001742266856228351, 7.952124684164948e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.477048447986008e-06, 0.33316263722171185, 0.33316263722171185, 0.33316263722171185, 0.00010957610544016206, 5.6883001114844596e-05, 9.819447511876074e-05, 7.072499501274399e-05, 0.00011619741618716382, 5.303529354271471e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990537273876834, 0.24990537273876834, 0.24990537273876834, 0.24990537273876834, 8.219306252838642e-05, 4.266795254908798e-05, 7.365569894054858e-05, 5.3050835435803445e-05, 8.715970928099788e-05, 3.9781786191955305e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 707.
Rec Success! in episode: 707.
total combined:  64
-----
It has processed 708 episodes
----target item:  992
[2.2555152658803984e-05, 0.9981171061275249, 0.0002787007943742394, 9.696932617673288e-05, 0.0003233006605194984, 0.0001672271696912719, 0.000291194120051185, 0.0002060470111082717, 0.00034171331156583357, 0.00015518632632920436]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 708.
Rec Success! in episode: 708.
total combined:  64
-----
It has processed 709 episodes
----target item:  1565
[0.9979675838173122, 1.4910060165633429e-05, 0.00030115000791527296, 0.00010636158214710071, 0.00034958581352435587, 0.00018124802935117612, 0.0003145314984019425, 0.00022459638427230094, 0.00036982967445722755, 0.00017020313245271582]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 709.
Rec Success! in episode: 709.
total combined:  64
-----
It has processed 710 episodes
----target item:  1496
[0.9979402110414397, 1.5004336147710818e-05, 0.00030324181817988993, 0.00010702065385254723, 0.0003553553068187774, 0.00018452889096650307, 0.0003189532986121439, 0.0002284206933181784, 0.00037590332282628537, 0.00017136063783812464]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 710.
Rec Success! in episode: 710.
total combined:  64
-----
It has processed 711 episodes
----target item:  1858
[2.3528000215512516e-05, 1.3887974884033785e-05, 0.9984089110517059, 9.509850345868758e-05, 0.000317632317370534, 0.0001636279517712446, 0.00028679848329800914, 0.00020319851944353335, 0.000333832505906621, 0.00015348469194600387]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 711.
Rec Success! in episode: 711.
total combined:  64
-----
It has processed 712 episodes
----target item:  1858
[0.9981349848103904, 1.4319798757566137e-05, 0.0002775693590972562, 9.650689839031041e-05, 0.0003216775948898367, 0.00016637343180649582, 0.0002900369354056926, 0.0002052818693489897, 0.000338313876026856, 0.00015493542588644417]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 712.
Rec Success! in episode: 712.
total combined:  64
-----
It has processed 713 episodes
----target item:  688
[2.2971358169604077e-05, 0.9980073662672941, 0.0002898568413129209, 0.00010330837050784177, 0.00034440991599974204, 0.00017686242324329137, 0.000308252810626259, 0.00021891037058391295, 0.0003621672721574584, 0.0001658943701051392]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 713.
Rec Success! in episode: 713.
total combined:  64
-----
It has processed 714 episodes
----target item:  778
[2.267612364355867e-05, 0.9980659457098382, 0.00028373572167050766, 9.799238646432263e-05, 0.00033333410705961277, 0.00017330871831890054, 0.000298282075080652, 0.0002122431419125711, 0.00035197539569187074, 0.00016050662031960204]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 714.
Rec Success! in episode: 714.
total combined:  64
-----
It has processed 715 episodes
----target item:  461
[2.3574650628811713e-05, 0.9979799174301366, 0.00029851578392324274, 0.00010319108147660107, 0.00034777050090921684, 0.0001814212032544701, 0.00031014573433724927, 0.0002205198193007918, 0.0003666944562319769, 0.00016824933980090072]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 715.
Rec Success! in episode: 715.
total combined:  64
-----
It has processed 716 episodes
----target item:  610
[2.4304350052619313e-05, 1.4402577284314724e-05, 0.00028393364697424636, 0.9981559051756999, 0.0003319378829078609, 0.00017080275552855368, 0.0002982166245563182, 0.00021202249823767307, 0.00034926103429943234, 0.0001592134544591866]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995446269721435, 7.208022373683216e-06, 0.00014209957284941707, 0.4995446269721435, 0.00016612413455184885, 8.548123429806943e-05, 0.00014924773945474475, 0.00010611037738958903, 0.00017479380945434943, 7.968116534136095e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331640432477417, 4.807285972411026e-06, 9.477124900980827e-05, 0.3331640432477417, 0.00011079408196980198, 5.701046934119152e-05, 0.3331640432477417, 7.076877710793713e-05, 0.0001165761958955747, 5.314219747838462e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24992379198181724, 3.5871986018068586e-06, 0.24992379198181724, 0.24992379198181724, 8.176978468012495e-05, 4.205094177900919e-05, 0.24992379198181724, 5.231059218198962e-05, 8.586552065101837e-05, 3.9248034836996834e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2192]
random_location_list [2192]
Random Combined Rec Success! in episode: 716.
Random Combined Rec Success! in episode: 716.
Rec Success! in episode: 716.
total combined:  65
-----
It has processed 717 episodes
----target item:  21
[2.3564067468305502e-05, 0.9980248592519997, 0.000291230841635362, 0.00010316590341842672, 0.00034107976330483404, 0.00017499155620838576, 0.00030398864384847176, 0.00021757475260800047, 0.00035776052035372586, 0.00016178469915462059]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 717.
Rec Success! in episode: 717.
total combined:  65
-----
It has processed 718 episodes
----target item:  85
[2.6562126407517992e-05, 1.5379400651903096e-05, 0.00030604306607655095, 0.998003118620495, 0.00035825602296644547, 0.0001867783382763894, 0.0003217362023935059, 0.0002306952740478041, 0.00037767028062861825, 0.00017376066805631674]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.49950692132830754, 7.697488042046808e-06, 0.00015317650504046673, 0.49950692132830754, 0.00017930942272670537, 9.348374868028244e-05, 0.0001610310197823675, 0.00011546445492464254, 0.00018902638241728332, 8.69683217711123e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331498919342237, 5.133897449415672e-06, 0.00010216222022587938, 0.3331498919342237, 0.00011959176590653695, 6.234968814370511e-05, 0.3331498919342237, 7.700988522460488e-05, 0.00012607256513597856, 5.800417524285644e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24991595162590327, 3.8512480348450365e-06, 0.24991595162590327, 0.24991595162590327, 8.97130412068554e-05, 4.677228485815889e-05, 0.24991595162590327, 5.776978836393739e-05, 9.457468200559265e-05, 4.3512451917457665e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.19994682150076767, 0.19994682150076767, 0.19994682150076767, 0.19994682150076767, 7.177548019555432e-05, 3.742045928191181e-05, 0.19994682150076767, 4.62190808029402e-05, 7.566506634906662e-05, 3.481240953208082e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 1, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16663891293747, 0.16663891293747, 0.16663891293747, 0.16663891293747, 0.16663891293747, 3.2178074452543525e-05, 0.16663891293747, 3.963273588573617e-05, 6.489760949729682e-05, 2.9813955344579782e-05]
[1, 0, 0, 1, 1, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2134]
random_location_list [2134]
Random Combined Rec Success! in episode: 718.
Random Combined Rec Success! in episode: 718.
Rec Success! in episode: 718.
total combined:  66
-----
It has processed 719 episodes
----target item:  210
[0.9979898960441282, 1.4850341031283127e-05, 0.00029638495598153874, 0.00010416578820845832, 0.00034920427911958464, 0.00017698954124763908, 0.0003118261037757261, 0.00022265287293786858, 0.0003663433076077309, 0.0001676867659620111]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 719.
Rec Success! in episode: 719.
total combined:  66
-----
It has processed 720 episodes
----target item:  1197
[2.3037485639880015e-05, 0.9980050369774921, 0.00029492116784999374, 0.00010345067761013077, 0.0003435561614994357, 0.0001769833477610356, 0.0003065439871746131, 0.0002192866797011759, 0.0003614092244527433, 0.00016577429081892712]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 720.
Rec Success! in episode: 720.
total combined:  66
-----
It has processed 721 episodes
----target item:  1431
[2.335730899664039e-05, 0.9979066887385893, 0.0003094710773830624, 0.00010928827235477763, 0.00036174125624013686, 0.00018583273148532032, 0.0003225430270068348, 0.00022997662724563315, 0.0003785792947264763, 0.00017252166597156899]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.335730899664039e-05, 0.9979066887385893, 0.0003094710773830624, 0.00010928827235477763, 0.00036174125624013686, 0.00018583273148532032, 0.0003225430270068348, 0.00022997662724563315, 0.0003785792947264763, 0.00017252166597156899]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1691530377999993e-05, 0.4995034473994729, 0.00015490613678386, 0.4995034473994729, 0.0001810700405134754, 9.301880733349225e-05, 0.00016144931759925286, 0.00011511508984442694, 0.00018949834184293446, 8.635593675880592e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.797740189318402e-06, 0.3331469859428494, 0.3331469859428494, 0.3331469859428494, 0.00012076580963688785, 6.203948233087663e-05, 0.00010767964429624012, 7.677673781406543e-05, 0.00012638711855706802, 5.759563862721375e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 9.058754757611205e-05, 4.653638785798379e-05, 8.077149426641187e-05, 5.759093911084853e-05, 9.480414323988428e-05, 4.3203019712340965e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 9.058754757611205e-05, 4.653638785798379e-05, 8.077149426641187e-05, 5.759093911084853e-05, 9.480414323988428e-05, 4.3203019712340965e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 9.058754757611205e-05, 4.653638785798379e-05, 8.077149426641187e-05, 5.759093911084853e-05, 9.480414323988428e-05, 4.3203019712340965e-05]
[-1, 0, 0, 1, -1, -1, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 9.058754757611205e-05, 4.653638785798379e-05, 8.077149426641187e-05, 5.759093911084853e-05, 9.480414323988428e-05, 4.3203019712340965e-05]
[-1, 0, 0, 1, -1, -1, -1, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 9.058754757611205e-05, 4.653638785798379e-05, 8.077149426641187e-05, 5.759093911084853e-05, 9.480414323988428e-05, 4.3203019712340965e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 0.24989662661705914, 9.058754757611205e-05, 4.653638785798379e-05, 8.077149426641187e-05, 5.759093911084853e-05, 9.480414323988428e-05, 4.3203019712340965e-05]
[-1, 0, 0, 1, -1, -1, -1, -1, -1, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
Max turn quit...
gamma: 0
total combined:  66
-----
It has processed 722 episodes
----target item:  2088
[2.2178107926853405e-05, 0.9980562242954727, 0.00028526530757407974, 0.00010001389437151612, 0.00033330260482721885, 0.00017269519997460981, 0.0003002206661772979, 0.0002157063542260242, 0.00035212026101015103, 0.00016227330843962047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 722.
Rec Success! in episode: 722.
total combined:  66
-----
It has processed 723 episodes
----target item:  2088
[2.584592392000044e-05, 1.5759571762808702e-05, 0.0003080881349780623, 0.00010832029204484808, 0.0003607203257724285, 0.00018628899229802478, 0.00032374543448451825, 0.00023224837864917837, 0.9982634476522982, 0.00017553529379191776]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2936186885699227e-05, 7.88784978990522e-06, 0.49964251848623165, 5.4215571698767504e-05, 0.00018054473742575198, 9.323981710133391e-05, 0.00016203837235018647, 0.00011624302692392814, 0.49964251848623165, 8.78574653611504e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331772888343145, 5.2598654247744085e-06, 0.3331772888343145, 3.615264218490547e-05, 0.00012039288872184494, 6.217523193852414e-05, 0.0001080522645477138, 7.751449310948874e-05, 0.3331772888343145, 5.8586111129150076e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991320069323886, 0.24991320069323886, 0.24991320069323886, 2.7117762298738657e-05, 9.030559155592245e-05, 4.6637066025614196e-05, 8.104900357929372e-05, 5.814290386023213e-05, 0.24991320069323886, 4.394489972495307e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 723.
Rec Success! in episode: 723.
total combined:  66
-----
It has processed 724 episodes
----target item:  2088
[0.9979548341708201, 1.537774054593508e-05, 0.00030099143742656347, 0.00010590672007915793, 0.0003520009014120711, 0.00018228144771874016, 0.00031710863684723063, 0.00022743337744027622, 0.0003722707169124927, 0.0001717948507974808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 724.
Rec Success! in episode: 724.
total combined:  66
-----
It has processed 725 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 725.
Rec Success! in episode: 725.
total combined:  66
-----
It has processed 726 episodes
----target item:  2088
[2.5246552968199034e-05, 1.5309616214596218e-05, 0.00029642319475306137, 0.00010438137104536884, 0.0003471268945488554, 0.00017941808634320617, 0.0003116439887053876, 0.0002235541071652365, 0.9983282250584026, 0.00016867112985366876]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2635711275791753e-05, 7.662348617432557e-06, 0.49965582335937747, 5.224209692158446e-05, 0.00017373441915442752, 8.979741272178712e-05, 0.00015597548968675266, 0.00011188716163412314, 0.49965582335937747, 8.441864123300839e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331831381456748, 5.109447821017652e-06, 0.3331831381456748, 3.483635130801749e-05, 0.00011585050403015943, 5.987918556988005e-05, 0.0001040084007792346, 7.460918874282114e-05, 0.3331831381456748, 5.629248472458478e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.249916463498204, 0.249916463498204, 0.249916463498204, 2.6130307099377397e-05, 8.689799976925312e-05, 4.491462076401413e-05, 7.801538769793713e-05, 5.5963410089869004e-05, 0.249916463498204, 4.222428176345433e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 726.
Rec Success! in episode: 726.
total combined:  66
-----
It has processed 727 episodes
----target item:  2088
[0.9980637148160619, 1.467316553857979e-05, 0.0002852674485212606, 0.00010001464498667862, 0.00033330510629954387, 0.00017269649607088133, 0.0003002229193660728, 0.00021570797312568958, 0.00035212290371103375, 0.0001622745263184617]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 727.
Rec Success! in episode: 727.
total combined:  66
-----
It has processed 728 episodes
----target item:  2088
[0.9979238696761253, 1.5633598884238815e-05, 0.0003055349769259411, 0.00010754251682060856, 0.00035760160457683053, 0.0001850299681975692, 0.00032185275568644817, 0.00023074732611053775, 0.00037795190269749045, 0.00017423567397513302]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 728.
Rec Success! in episode: 728.
total combined:  66
-----
It has processed 729 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 729.
Rec Success! in episode: 729.
total combined:  66
-----
It has processed 730 episodes
----target item:  2088
[0.998024285812606, 1.4628647156443813e-05, 0.00029057837173553054, 0.00010209315627159911, 0.00034019260770540744, 0.00017640070332104607, 0.0003064085723472314, 0.00022002418186393467, 0.0003593142617455842, 0.0001660736852474917]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 730.
Rec Success! in episode: 730.
total combined:  66
-----
It has processed 731 episodes
----target item:  2088
[2.4612491505257546e-05, 1.494897082580244e-05, 0.00029036033370669664, 0.00010250511542228324, 0.00034142342526631233, 0.00017625729463582724, 0.000306084375095758, 0.00021968160769441866, 0.9983579139017958, 0.00016621248405181282]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.231814783304263e-05, 7.481714419068072e-06, 0.4996617417258782, 5.1302127017293626e-05, 0.0001708768177815653, 8.821388161830277e-05, 0.00015319020347893727, 0.00010994703722710367, 0.4996617417258782, 8.31866188683138e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318569918409646, 4.988975624194415e-06, 0.33318569918409646, 3.42094133540163e-05, 0.00011394450935997208, 5.88230023840048e-05, 0.00010215067673179078, 7.331515986234885e-05, 0.33318569918409646, 5.547071039432476e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991788182413435, 0.24991788182413435, 0.24991788182413435, 2.5659997247235077e-05, 8.546816533383111e-05, 4.412230235074923e-05, 7.662177824026368e-05, 5.4992664761016834e-05, 0.24991788182413435, 4.16077955295728e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 731.
Rec Success! in episode: 731.
total combined:  66
-----
It has processed 732 episodes
----target item:  2088
[2.2178107926853405e-05, 0.9980562242954727, 0.00028526530757407974, 0.00010001389437151612, 0.00033330260482721885, 0.00017269519997460981, 0.0003002206661772979, 0.0002157063542260242, 0.00035212026101015103, 0.00016227330843962047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 732.
Rec Success! in episode: 732.
total combined:  66
-----
It has processed 733 episodes
----target item:  2088
[2.2436120319181806e-05, 0.9980229797542908, 0.00028940171638242317, 0.00010180228515673222, 0.00033978267574302936, 0.00017568930941898076, 0.0003052878614643487, 0.00021894921550589752, 0.0003583248828817847, 0.00016534617883674036]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 733.
Rec Success! in episode: 733.
total combined:  66
-----
It has processed 734 episodes
----target item:  2088
[0.9979861729045157, 1.5121870271061513e-05, 0.00029666244220463424, 0.00010439367094973585, 0.00034686041118640924, 0.0001797819112065007, 0.0003118601553551373, 0.00022401567432876515, 0.000365945413095028, 0.00016918554688672056]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 734.
Rec Success! in episode: 734.
total combined:  66
-----
It has processed 735 episodes
----target item:  2088
[0.9980637148160619, 1.467316553857979e-05, 0.0002852674485212606, 0.00010001464498667862, 0.00033330510629954387, 0.00017269649607088133, 0.0003002229193660728, 0.00021570797312568958, 0.00035212290371103375, 0.0001622745263184617]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 735.
Rec Success! in episode: 735.
total combined:  66
-----
It has processed 736 episodes
----target item:  2088
[0.9979907943075087, 1.4942788813025944e-05, 0.0002960178168956547, 0.0001039360595557907, 0.0003461063214010922, 0.00017926913421954365, 0.00031144391361552634, 0.00022372541929265236, 0.00036515747470947855, 0.00016860676398841161]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 736.
Rec Success! in episode: 736.
total combined:  66
-----
It has processed 737 episodes
----target item:  2088
[2.2975735630925037e-05, 0.9979910376308215, 0.00029485467712015107, 0.00010387530152506859, 0.00034485408205656116, 0.00017838234302796312, 0.000310101765438744, 0.00022229408356148398, 0.00036391519268363947, 0.0001677091881339542]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 737.
Rec Success! in episode: 737.
total combined:  66
-----
It has processed 738 episodes
----target item:  2088
[0.9980305977511896, 1.4803203908295104e-05, 0.0002894039254110955, 0.0001018030622224996, 0.0003397852693339813, 0.00017569065047088185, 0.0003052901917533592, 0.00021895088676445425, 0.00035832761800702926, 0.00016534744093861897]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 738.
Rec Success! in episode: 738.
total combined:  66
-----
It has processed 739 episodes
----target item:  2088
[2.429476312874459e-05, 1.4779272548606866e-05, 0.0002898773304445745, 0.0001019441222818712, 0.00033910611169489236, 0.00017588862628796744, 0.0003052497819035073, 0.0002192616753399107, 0.9983638676173024, 0.0001657306990674546]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2159090827891046e-05, 7.396759389518428e-06, 0.49966311181197565, 5.102119479931541e-05, 0.00016971649365507625, 8.802908558091767e-05, 0.00015277201114043004, 0.00010973651446632963, 0.49966311181197565, 8.294522618937708e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318627304928966, 4.932320668417444e-06, 0.33318627304928966, 3.402204673476611e-05, 0.00011317066371152712, 5.8699716371457687e-05, 0.0001018717127897142, 7.317470393174521e-05, 0.33318627304928966, 5.5309687923627326e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.249918194074929, 0.249918194074929, 0.249918194074929, 2.5519444126162236e-05, 8.488767450771261e-05, 4.4029806432316725e-05, 7.641249519291834e-05, 5.488728479484507e-05, 0.249918194074929, 4.148699523007052e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 739.
Rec Success! in episode: 739.
total combined:  66
-----
It has processed 740 episodes
----target item:  2088
[2.2178107926853405e-05, 0.9980562242954727, 0.00028526530757407974, 0.00010001389437151612, 0.00033330260482721885, 0.00017269519997460981, 0.0003002206661772979, 0.0002157063542260242, 0.00035212026101015103, 0.00016227330843962047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 740.
Rec Success! in episode: 740.
total combined:  66
-----
It has processed 741 episodes
----target item:  2088
[2.4612491505257546e-05, 1.494897082580244e-05, 0.00029036033370669664, 0.00010250511542228324, 0.00034142342526631233, 0.00017625729463582724, 0.000306084375095758, 0.00021968160769441866, 0.9983579139017958, 0.00016621248405181282]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.231814783304263e-05, 7.481714419068072e-06, 0.4996617417258782, 5.1302127017293626e-05, 0.0001708768177815653, 8.821388161830277e-05, 0.00015319020347893727, 0.00010994703722710367, 0.4996617417258782, 8.31866188683138e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33318569918409646, 4.988975624194415e-06, 0.33318569918409646, 3.42094133540163e-05, 0.00011394450935997208, 5.88230023840048e-05, 0.00010215067673179078, 7.331515986234885e-05, 0.33318569918409646, 5.547071039432476e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991788182413435, 0.24991788182413435, 0.24991788182413435, 2.5659997247235077e-05, 8.546816533383111e-05, 4.412230235074923e-05, 7.662177824026368e-05, 5.4992664761016834e-05, 0.24991788182413435, 4.16077955295728e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 741.
Rec Success! in episode: 741.
total combined:  66
-----
It has processed 742 episodes
----target item:  2088
[2.2975735630925037e-05, 0.9979910376308215, 0.00029485467712015107, 0.00010387530152506859, 0.00034485408205656116, 0.00017838234302796312, 0.000310101765438744, 0.00022229408356148398, 0.00036391519268363947, 0.0001677091881339542]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 742.
Rec Success! in episode: 742.
total combined:  66
-----
It has processed 743 episodes
----target item:  2088
[2.5749273865040943e-05, 1.557548376566099e-05, 0.00030100618523967894, 0.00010571338938228085, 0.00035196535312856977, 0.0001827623539332246, 0.00031667602783566986, 0.00022705029709460132, 0.9983018040489969, 0.00017169758675831013]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.288751931058877e-05, 7.7955343072506e-06, 0.49965035305109556, 5.2909583166988e-05, 0.0001761587650539918, 9.147261308835926e-05, 0.00015849644713568522, 0.00011363874195513898, 0.49965035305109556, 8.593469379085709e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331807617075738, 5.198279241767432e-06, 0.3331807617075738, 3.528158263785827e-05, 0.0001174675673973805, 6.099648427756656e-05, 0.0001056898422309561, 7.577747593471978e-05, 0.3331807617075738, 5.730364555835091e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991514309696897, 0.24991514309696897, 0.24991514309696897, 2.6464318433147546e-05, 8.811110150812124e-05, 4.575277701663751e-05, 7.92767622886584e-05, 5.68398326622894e-05, 0.24991514309696897, 4.298282021535973e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 743.
Rec Success! in episode: 743.
total combined:  66
-----
It has processed 744 episodes
----target item:  2088
[0.9980637148160619, 1.467316553857979e-05, 0.0002852674485212606, 0.00010001464498667862, 0.00033330510629954387, 0.00017269649607088133, 0.0003002229193660728, 0.00021570797312568958, 0.00035212290371103375, 0.0001622745263184617]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 744.
Rec Success! in episode: 744.
total combined:  66
-----
It has processed 745 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 745.
Rec Success! in episode: 745.
total combined:  66
-----
It has processed 746 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 746.
Rec Success! in episode: 746.
total combined:  66
-----
It has processed 747 episodes
----target item:  2088
[0.998024285812606, 1.4628647156443813e-05, 0.00029057837173553054, 0.00010209315627159911, 0.00034019260770540744, 0.00017640070332104607, 0.0003064085723472314, 0.00022002418186393467, 0.0003593142617455842, 0.0001660736852474917]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 747.
Rec Success! in episode: 747.
total combined:  66
-----
It has processed 748 episodes
----target item:  2088
[2.3673745038917372e-05, 0.9979158460969243, 0.000305532520341666, 0.00010754165214953754, 0.0003575987293627146, 0.00018502848050632392, 0.00032185016790279577, 0.00023074547083930643, 0.00037794886386144534, 0.00017423427307294772]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 748.
Rec Success! in episode: 748.
total combined:  66
-----
It has processed 749 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 749.
Rec Success! in episode: 749.
total combined:  66
-----
It has processed 750 episodes
----target item:  2088
[2.4207447956951742e-05, 1.4752226840085614e-05, 0.00028760581240758735, 0.00010083926769030235, 0.00033604509642229825, 0.0001741051146560815, 0.0003022422093706787, 0.00021721616312077213, 0.9983794776666108, 0.00016350899492429668]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2115282734465833e-05, 7.3831574252868265e-06, 0.49966645264420595, 5.046778334407859e-05, 0.0001681830055744398, 8.713569035968015e-05, 0.00015126542158954982, 0.00010871179958266803, 0.49966645264420595, 8.183257097811147e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331877488003877, 4.923239470154792e-06, 0.3331877488003877, 3.365294393965001e-05, 0.00011214784726348678, 5.810384979313886e-05, 0.00010086685832929332, 7.249123806352485e-05, 0.3331877488003877, 5.456762197753497e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991902266683025, 0.24991902266683025, 0.24991902266683025, 2.5242557355545756e-05, 8.412038102598733e-05, 4.358280700825298e-05, 7.565868416198284e-05, 5.4374566393791634e-05, 0.24991902266683025, 4.093033673350572e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 750.
Rec Success! in episode: 750.
total combined:  66
-----
It has processed 751 episodes
----target item:  2088
[0.9979548341708201, 1.537774054593508e-05, 0.00030099143742656347, 0.00010590672007915793, 0.0003520009014120711, 0.00018228144771874016, 0.00031710863684723063, 0.00022743337744027622, 0.0003722707169124927, 0.0001717948507974808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 751.
Rec Success! in episode: 751.
total combined:  66
-----
It has processed 752 episodes
----target item:  2088
[0.998024285812606, 1.4628647156443813e-05, 0.00029057837173553054, 0.00010209315627159911, 0.00034019260770540744, 0.00017640070332104607, 0.0003064085723472314, 0.00022002418186393467, 0.0003593142617455842, 0.0001660736852474917]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 752.
Rec Success! in episode: 752.
total combined:  66
-----
It has processed 753 episodes
----target item:  2088
[2.5749273865040943e-05, 1.557548376566099e-05, 0.00030100618523967894, 0.00010571338938228085, 0.00035196535312856977, 0.0001827623539332246, 0.00031667602783566986, 0.00022705029709460132, 0.9983018040489969, 0.00017169758675831013]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.288751931058877e-05, 7.7955343072506e-06, 0.49965035305109556, 5.2909583166988e-05, 0.0001761587650539918, 9.147261308835926e-05, 0.00015849644713568522, 0.00011363874195513898, 0.49965035305109556, 8.593469379085709e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331807617075738, 5.198279241767432e-06, 0.3331807617075738, 3.528158263785827e-05, 0.0001174675673973805, 6.099648427756656e-05, 0.0001056898422309561, 7.577747593471978e-05, 0.3331807617075738, 5.730364555835091e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991514309696897, 0.24991514309696897, 0.24991514309696897, 2.6464318433147546e-05, 8.811110150812124e-05, 4.575277701663751e-05, 7.92767622886584e-05, 5.68398326622894e-05, 0.24991514309696897, 4.298282021535973e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 753.
Rec Success! in episode: 753.
total combined:  66
-----
It has processed 754 episodes
----target item:  2088
[2.4207447956951742e-05, 1.4752226840085614e-05, 0.00028760581240758735, 0.00010083926769030235, 0.00033604509642229825, 0.0001741051146560815, 0.0003022422093706787, 0.00021721616312077213, 0.9983794776666108, 0.00016350899492429668]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2115282734465833e-05, 7.3831574252868265e-06, 0.49966645264420595, 5.046778334407859e-05, 0.0001681830055744398, 8.713569035968015e-05, 0.00015126542158954982, 0.00010871179958266803, 0.49966645264420595, 8.183257097811147e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331877488003877, 4.923239470154792e-06, 0.3331877488003877, 3.365294393965001e-05, 0.00011214784726348678, 5.810384979313886e-05, 0.00010086685832929332, 7.249123806352485e-05, 0.3331877488003877, 5.456762197753497e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991902266683025, 0.24991902266683025, 0.24991902266683025, 2.5242557355545756e-05, 8.412038102598733e-05, 4.358280700825298e-05, 7.565868416198284e-05, 5.4374566393791634e-05, 0.24991902266683025, 4.093033673350572e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 754.
Rec Success! in episode: 754.
total combined:  66
-----
It has processed 755 episodes
----target item:  2088
[2.26568315654158e-05, 0.9979830956488154, 0.0002960155333674374, 0.00010393525777660293, 0.00034610365148223595, 0.00017926775130911352, 0.00031144151108796126, 0.00022372369343941407, 0.00036515465782701516, 0.00016860546332919037]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 755.
Rec Success! in episode: 755.
total combined:  66
-----
It has processed 756 episodes
----target item:  2088
[2.581650070764525e-05, 1.570849751708522e-05, 0.00030397846349393626, 0.00010693824330465217, 0.000355449849416439, 0.00018424593235485398, 0.00031973811612944674, 0.0002292305840500461, 0.9982856928028612, 0.00017320101016479603]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2921289780763322e-05, 7.862182823970056e-06, 0.49964706165138467, 5.352313413939891e-05, 0.0001779044557141848, 9.221602531821713e-05, 0.00016003055174865208, 0.00011473107206381075, 0.49964706165138467, 8.668798564158277e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331793056744532, 5.242733952478745e-06, 0.3331793056744532, 3.569079464041342e-05, 0.0001186319055601702, 6.14923485910912e-05, 0.0001067130625007405, 7.65060416910393e-05, 0.3331793056744532, 5.780608970443943e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991433222124046, 0.24991433222124046, 0.24991433222124046, 2.6771293886180482e-05, 8.898455862433375e-05, 4.6124771176136805e-05, 8.004435839785993e-05, 5.738638623248835e-05, 0.24991433222124046, 4.3359746721249635e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 756.
Rec Success! in episode: 756.
total combined:  66
-----
It has processed 757 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 757.
Rec Success! in episode: 757.
total combined:  66
-----
It has processed 758 episodes
----target item:  2088
[0.9979861729045157, 1.5121870271061513e-05, 0.00029666244220463424, 0.00010439367094973585, 0.00034686041118640924, 0.0001797819112065007, 0.0003118601553551373, 0.00022401567432876515, 0.000365945413095028, 0.00016918554688672056]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 758.
Rec Success! in episode: 758.
total combined:  66
-----
It has processed 759 episodes
----target item:  2088
[2.4207447956951742e-05, 1.4752226840085614e-05, 0.00028760581240758735, 0.00010083926769030235, 0.00033604509642229825, 0.0001741051146560815, 0.0003022422093706787, 0.00021721616312077213, 0.9983794776666108, 0.00016350899492429668]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2115282734465833e-05, 7.3831574252868265e-06, 0.49966645264420595, 5.046778334407859e-05, 0.0001681830055744398, 8.713569035968015e-05, 0.00015126542158954982, 0.00010871179958266803, 0.49966645264420595, 8.183257097811147e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331877488003877, 4.923239470154792e-06, 0.3331877488003877, 3.365294393965001e-05, 0.00011214784726348678, 5.810384979313886e-05, 0.00010086685832929332, 7.249123806352485e-05, 0.3331877488003877, 5.456762197753497e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991902266683025, 0.24991902266683025, 0.24991902266683025, 2.5242557355545756e-05, 8.412038102598733e-05, 4.358280700825298e-05, 7.565868416198284e-05, 5.4374566393791634e-05, 0.24991902266683025, 4.093033673350572e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 759.
Rec Success! in episode: 759.
total combined:  66
-----
It has processed 760 episodes
----target item:  2088
[0.9979499179264167, 1.555348471654879e-05, 0.00030156327029612833, 0.00010604174355769992, 0.0003535755950356152, 0.0001828840892744254, 0.00031752528727975514, 0.00022788659418363768, 0.00037293367244921474, 0.00017211833679049308]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 760.
Rec Success! in episode: 760.
total combined:  66
-----
It has processed 761 episodes
----target item:  2088
[2.340128252994334e-05, 0.9979468269151764, 0.00030098902237199037, 0.0001059058703190756, 0.00035199807707462827, 0.00018227998515340051, 0.00031710609247364267, 0.0002274315525909617, 0.0003722677299368332, 0.00017179347237308574]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 761.
Rec Success! in episode: 761.
total combined:  66
-----
It has processed 762 episodes
----target item:  2088
[2.581650070764525e-05, 1.570849751708522e-05, 0.00030397846349393626, 0.00010693824330465217, 0.000355449849416439, 0.00018424593235485398, 0.00031973811612944674, 0.0002292305840500461, 0.9982856928028612, 0.00017320101016479603]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2921289780763322e-05, 7.862182823970056e-06, 0.49964706165138467, 5.352313413939891e-05, 0.0001779044557141848, 9.221602531821713e-05, 0.00016003055174865208, 0.00011473107206381075, 0.49964706165138467, 8.668798564158277e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331793056744532, 5.242733952478745e-06, 0.3331793056744532, 3.569079464041342e-05, 0.0001186319055601702, 6.14923485910912e-05, 0.0001067130625007405, 7.65060416910393e-05, 0.3331793056744532, 5.780608970443943e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991433222124046, 0.24991433222124046, 0.24991433222124046, 2.6771293886180482e-05, 8.898455862433375e-05, 4.6124771176136805e-05, 8.004435839785993e-05, 5.738638623248835e-05, 0.24991433222124046, 4.3359746721249635e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 762.
Rec Success! in episode: 762.
total combined:  66
-----
It has processed 763 episodes
----target item:  2088
[2.5749273865040943e-05, 1.557548376566099e-05, 0.00030100618523967894, 0.00010571338938228085, 0.00035196535312856977, 0.0001827623539332246, 0.00031667602783566986, 0.00022705029709460132, 0.9983018040489969, 0.00017169758675831013]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.288751931058877e-05, 7.7955343072506e-06, 0.49965035305109556, 5.2909583166988e-05, 0.0001761587650539918, 9.147261308835926e-05, 0.00015849644713568522, 0.00011363874195513898, 0.49965035305109556, 8.593469379085709e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331807617075738, 5.198279241767432e-06, 0.3331807617075738, 3.528158263785827e-05, 0.0001174675673973805, 6.099648427756656e-05, 0.0001056898422309561, 7.577747593471978e-05, 0.3331807617075738, 5.730364555835091e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991514309696897, 0.24991514309696897, 0.24991514309696897, 2.6464318433147546e-05, 8.811110150812124e-05, 4.575277701663751e-05, 7.92767622886584e-05, 5.68398326622894e-05, 0.24991514309696897, 4.298282021535973e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 763.
Rec Success! in episode: 763.
total combined:  66
-----
It has processed 764 episodes
----target item:  2088
[2.2436120319181806e-05, 0.9980229797542908, 0.00028940171638242317, 0.00010180228515673222, 0.00033978267574302936, 0.00017568930941898076, 0.0003052878614643487, 0.00021894921550589752, 0.0003583248828817847, 0.00016534617883674036]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 764.
Rec Success! in episode: 764.
total combined:  66
-----
It has processed 765 episodes
----target item:  2088
[0.9979548341708201, 1.537774054593508e-05, 0.00030099143742656347, 0.00010590672007915793, 0.0003520009014120711, 0.00018228144771874016, 0.00031710863684723063, 0.00022743337744027622, 0.0003722707169124927, 0.0001717948507974808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 765.
Rec Success! in episode: 765.
total combined:  66
-----
It has processed 766 episodes
----target item:  2088
[0.9980305977511896, 1.4803203908295104e-05, 0.0002894039254110955, 0.0001018030622224996, 0.0003397852693339813, 0.00017569065047088185, 0.0003052901917533592, 0.00021895088676445425, 0.00035832761800702926, 0.00016534744093861897]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 766.
Rec Success! in episode: 766.
total combined:  66
-----
It has processed 767 episodes
----target item:  2088
[0.9980676162251719, 1.4602151680806719e-05, 0.00028461294212155954, 9.995531531693242e-05, 0.000333114846303437, 0.00017227287187173356, 0.00029940029640706736, 0.0002147214135706749, 0.0003513629237711526, 0.00016234101378487676]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 767.
Rec Success! in episode: 767.
total combined:  66
-----
It has processed 768 episodes
----target item:  2088
[0.9979548341708201, 1.537774054593508e-05, 0.00030099143742656347, 0.00010590672007915793, 0.0003520009014120711, 0.00018228144771874016, 0.00031710863684723063, 0.00022743337744027622, 0.0003722707169124927, 0.0001717948507974808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 768.
Rec Success! in episode: 768.
total combined:  66
-----
It has processed 769 episodes
----target item:  2088
[0.9979548341708201, 1.537774054593508e-05, 0.00030099143742656347, 0.00010590672007915793, 0.0003520009014120711, 0.00018228144771874016, 0.00031710863684723063, 0.00022743337744027622, 0.0003722707169124927, 0.0001717948507974808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 769.
Rec Success! in episode: 769.
total combined:  66
-----
It has processed 770 episodes
----target item:  2088
[2.2178107926853405e-05, 0.9980562242954727, 0.00028526530757407974, 0.00010001389437151612, 0.00033330260482721885, 0.00017269519997460981, 0.0003002206661772979, 0.0002157063542260242, 0.00035212026101015103, 0.00016227330843962047]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 770.
Rec Success! in episode: 770.
total combined:  66
-----
It has processed 771 episodes
----target item:  2088
[0.9980637148160619, 1.467316553857979e-05, 0.0002852674485212606, 0.00010001464498667862, 0.00033330510629954387, 0.00017269649607088133, 0.0003002229193660728, 0.00021570797312568958, 0.00035212290371103375, 0.0001622745263184617]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 771.
Rec Success! in episode: 771.
total combined:  66
-----
It has processed 772 episodes
----target item:  2088
[2.3692183275578747e-05, 0.9979417957865301, 0.0003015608159254009, 0.00010604088050249091, 0.0003535727173456713, 0.0001828826008128008, 0.0003175227029969625, 0.0002278847394544945, 0.00037293063720726357, 0.00017211693594944549]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 772.
Rec Success! in episode: 772.
total combined:  66
-----
It has processed 773 episodes
----target item:  2088
[2.3673745038917372e-05, 0.9979158460969243, 0.000305532520341666, 0.00010754165214953754, 0.0003575987293627146, 0.00018502848050632392, 0.00032185016790279577, 0.00023074547083930643, 0.00037794886386144534, 0.00017423427307294772]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 773.
Rec Success! in episode: 773.
total combined:  66
-----
It has processed 774 episodes
----target item:  2088
[0.9980637148160619, 1.467316553857979e-05, 0.0002852674485212606, 0.00010001464498667862, 0.00033330510629954387, 0.00017269649607088133, 0.0003002229193660728, 0.00021570797312568958, 0.00035212290371103375, 0.0001622745263184617]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 774.
Rec Success! in episode: 774.
total combined:  66
-----
It has processed 775 episodes
----target item:  2088
[2.5822780189708527e-05, 1.5620844662736527e-05, 0.00030242021692596425, 0.00010660220400281732, 0.0003552114376362057, 0.00018347710263265366, 0.0003182959750329992, 0.00022840981763965574, 0.9982915198572384, 0.00017261976403881707]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2924384919996442e-05, 7.818283225643554e-06, 0.499648131232025, 5.3354747541920195e-05, 0.0001777844722476977, 9.183088269384656e-05, 0.0001593081639385822, 0.00011431985173531485, 0.499648131232025, 8.63967496468789e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317978195677733, 5.213456705968539e-06, 0.33317978195677733, 3.557848421956926e-05, 0.00011855181275817014, 6.123548065193509e-05, 0.00010623127758751296, 7.623177370959812e-05, 0.33317978195677733, 5.76118440354058e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991459470430144, 0.24991459470430144, 0.24991459470430144, 2.6687040887374497e-05, 8.892444812501221e-05, 4.593207978819303e-05, 7.968294632790039e-05, 5.718063898815966e-05, 0.24991459470430144, 4.3214028677597525e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 775.
Rec Success! in episode: 775.
total combined:  66
-----
It has processed 776 episodes
----target item:  2088
[0.9979335574587598, 1.5364829806441534e-05, 0.0003041903307382537, 0.0001070635419328291, 0.0003563244637823815, 0.00018416620362558011, 0.0003203912355590728, 0.00022941709957206169, 0.000375767741204805, 0.0001737570950186935]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 776.
Rec Success! in episode: 776.
total combined:  66
-----
It has processed 777 episodes
----target item:  2088
[0.9979548341708201, 1.537774054593508e-05, 0.00030099143742656347, 0.00010590672007915793, 0.0003520009014120711, 0.00018228144771874016, 0.00031710863684723063, 0.00022743337744027622, 0.0003722707169124927, 0.0001717948507974808]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 777.
Rec Success! in episode: 777.
total combined:  66
-----
It has processed 778 episodes
----target item:  2088
[2.5749273865040943e-05, 1.557548376566099e-05, 0.00030100618523967894, 0.00010571338938228085, 0.00035196535312856977, 0.0001827623539332246, 0.00031667602783566986, 0.00022705029709460132, 0.9983018040489969, 0.00017169758675831013]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.288751931058877e-05, 7.7955343072506e-06, 0.49965035305109556, 5.2909583166988e-05, 0.0001761587650539918, 9.147261308835926e-05, 0.00015849644713568522, 0.00011363874195513898, 0.49965035305109556, 8.593469379085709e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331807617075738, 5.198279241767432e-06, 0.3331807617075738, 3.528158263785827e-05, 0.0001174675673973805, 6.099648427756656e-05, 0.0001056898422309561, 7.577747593471978e-05, 0.3331807617075738, 5.730364555835091e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991514309696897, 0.24991514309696897, 0.24991514309696897, 2.6464318433147546e-05, 8.811110150812124e-05, 4.575277701663751e-05, 7.92767622886584e-05, 5.68398326622894e-05, 0.24991514309696897, 4.298282021535973e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 778.
Rec Success! in episode: 778.
total combined:  66
-----
It has processed 779 episodes
----target item:  2088
[2.4207447956951742e-05, 1.4752226840085614e-05, 0.00028760581240758735, 0.00010083926769030235, 0.00033604509642229825, 0.0001741051146560815, 0.0003022422093706787, 0.00021721616312077213, 0.9983794776666108, 0.00016350899492429668]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2115282734465833e-05, 7.3831574252868265e-06, 0.49966645264420595, 5.046778334407859e-05, 0.0001681830055744398, 8.713569035968015e-05, 0.00015126542158954982, 0.00010871179958266803, 0.49966645264420595, 8.183257097811147e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331877488003877, 4.923239470154792e-06, 0.3331877488003877, 3.365294393965001e-05, 0.00011214784726348678, 5.810384979313886e-05, 0.00010086685832929332, 7.249123806352485e-05, 0.3331877488003877, 5.456762197753497e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991902266683025, 0.24991902266683025, 0.24991902266683025, 2.5242557355545756e-05, 8.412038102598733e-05, 4.358280700825298e-05, 7.565868416198284e-05, 5.4374566393791634e-05, 0.24991902266683025, 4.093033673350572e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 779.
Rec Success! in episode: 779.
total combined:  66
-----
It has processed 780 episodes
----target item:  2088
[0.9979861729045157, 1.5121870271061513e-05, 0.00029666244220463424, 0.00010439367094973585, 0.00034686041118640924, 0.0001797819112065007, 0.0003118601553551373, 0.00022401567432876515, 0.000365945413095028, 0.00016918554688672056]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 780.
Rec Success! in episode: 780.
total combined:  66
-----
It has processed 781 episodes
----target item:  2089
[2.384930601136963e-05, 1.45092090363851e-05, 0.000276993220908644, 9.674785208934685e-05, 0.0003232600294101008, 0.0001675462942039463, 0.00029181060804308744, 0.0002097052538964011, 0.998438410314158, 0.00015716791224266094]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.193562532403589e-05, 7.26127975060785e-06, 0.499678555382477, 4.841843669971726e-05, 0.00016177873651486636, 8.385022990168531e-05, 0.0001460395569380916, 0.00010494910576416892, 0.499678555382477, 7.865626415272049e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319309025054644, 4.841929302783107e-06, 0.33319309025054644, 3.228613350583069e-05, 0.00010787646693173969, 5.59125800341302e-05, 9.738134797035116e-05, 6.998162417001971e-05, 0.33319309025054644, 5.244916644571152e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.249922012641579, 0.249922012641579, 0.249922012641579, 2.421723529777998e-05, 8.091615498979847e-05, 4.1938998565683094e-05, 7.304395916553732e-05, 5.2491929971735696e-05, 0.249922012641579, 3.934115569332068e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 781.
Rec Success! in episode: 781.
total combined:  66
-----
It has processed 782 episodes
----target item:  2089
[0.998024285812606, 1.4628647156443813e-05, 0.00029057837173553054, 0.00010209315627159911, 0.00034019260770540744, 0.00017640070332104607, 0.0003064085723472314, 0.00022002418186393467, 0.0003593142617455842, 0.0001660736852474917]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 782.
Rec Success! in episode: 782.
total combined:  66
-----
It has processed 783 episodes
----target item:  2089
[2.2136197052825496e-05, 0.9980167929858726, 0.0002905761901719926, 0.00010209238979092175, 0.0003401900536550684, 0.0001763993789645906, 0.0003064062719359339, 0.00022002252999724634, 0.0003593115641363733, 0.00016607243842277388]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2136197052825496e-05, 0.9980167929858726, 0.0002905761901719926, 0.00010209238979092175, 0.0003401900536550684, 0.0001763993789645906, 0.0003064062719359339, 0.00022002252999724634, 0.0003593115641363733, 0.00016607243842277388]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.107965072093474e-05, 0.499529230496233, 0.00014543973778525108, 0.499529230496233, 0.00017027256146299539, 8.829174684582954e-05, 0.00015336303989580584, 0.00011012608793138274, 0.00017984329562677122, 8.312288726501978e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.389469453534785e-06, 0.3331563496785245, 0.3331563496785245, 0.3331563496785245, 0.0001135616928183976, 5.888535503052763e-05, 0.00010228404551327632, 7.344756466633309e-05, 0.00011994480448251302, 5.543803246197088e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990181864318986, 0.24990181864318986, 0.24990181864318986, 0.24990181864318986, 8.518304871241716e-05, 4.417012411073172e-05, 7.67236434683455e-05, 5.509329179149993e-05, 8.997104454381651e-05, 4.158427461345115e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 783.
Rec Success! in episode: 783.
total combined:  66
-----
It has processed 784 episodes
----target item:  2089
[2.376763291714835e-05, 1.4418312149808888e-05, 0.00027302398844447775, 9.580887100061861e-05, 0.00031923081423788804, 0.00016505484259301973, 0.00028708719920386195, 0.0002061426638053085, 0.998460268327131, 0.00015519734851689485]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1894597458014704e-05, 7.215696221992812e-06, 0.4996830357895604, 4.794789440882814e-05, 0.00015976021023171913, 8.260229018109148e-05, 0.00014367382236937228, 0.0001031648382249246, 0.4996830357895604, 7.766907178323945e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319507328277165, 4.811519021601621e-06, 0.33319507328277165, 3.197227251483542e-05, 0.00010653016240928944, 5.508026920850804e-05, 9.580355214088112e-05, 6.879164064123945e-05, 0.33319507328277165, 5.1790735748571894e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992312263215133, 0.24992312263215133, 0.24992312263215133, 2.3981777719061314e-05, 7.990619603563176e-05, 4.131463511865091e-05, 7.186037498814113e-05, 5.159926727204806e-05, 0.24992312263215133, 3.884722026101144e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 784.
Rec Success! in episode: 784.
total combined:  66
-----
It has processed 785 episodes
----target item:  2089
[2.3538229213301382e-05, 1.4297390070360204e-05, 0.00027807126066821543, 9.763518458202329e-05, 0.00032560784669692573, 0.00016883946625571394, 0.00029380038812449455, 0.00021087642110168545, 0.9984286530014284, 0.00015868081185895064]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1780007687306135e-05, 7.1553116171577624e-06, 0.4996763818128319, 4.8862776146212615e-05, 0.00016295460896308467, 8.449786907882758e-05, 0.0001470361597415445, 0.00010553580046903818, 0.4996763818128319, 7.941384063292676e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319208922539884, 4.77127459602962e-06, 0.33319208922539884, 3.258246949844422e-05, 0.00010866070237767591, 5.6344511284134863e-05, 9.804602946856068e-05, 7.037293561640707e-05, 0.33319208922539884, 5.295440096227944e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992143619963106, 0.24992143619963106, 0.24992143619963106, 2.4439528534163997e-05, 8.150445246110997e-05, 4.226301175047187e-05, 7.354257586193058e-05, 5.2785482331601326e-05, 0.24992143619963106, 3.972015053644064e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 785.
Rec Success! in episode: 785.
total combined:  66
-----
It has processed 786 episodes
----target item:  1711
[2.2904898511184183e-05, 0.9980296879243428, 0.0002880957317038996, 0.00010079890017967764, 0.0003408951063990768, 0.00017540507409694853, 0.0003038933034379093, 0.00021721817500630828, 0.0003577654329965323, 0.00016333545332592212]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 786.
Rec Success! in episode: 786.
total combined:  66
-----
It has processed 787 episodes
----target item:  1255
[0.998078408703921, 1.5270533078638856e-05, 0.00028283816973813847, 0.00010042061618866097, 0.0003312603989234485, 0.0001729785401061421, 0.0002966802603136064, 0.00021203062159830537, 0.0003502273686222396, 0.0001598847875099175]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 787.
Rec Success! in episode: 787.
total combined:  66
-----
It has processed 788 episodes
----target item:  800
[0.998061048563835, 1.4355405392804547e-05, 0.00028615430423122886, 9.9071887302444e-05, 0.0003369816061121884, 0.00017491643892674605, 0.00029752763621027404, 0.00021423100723109412, 0.0003534941414274969, 0.0001622190093308642]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 788.
Rec Success! in episode: 788.
total combined:  66
-----
It has processed 789 episodes
----target item:  1110
[2.2968636179739318e-05, 0.9980771063697577, 0.0002841256136830965, 9.876644471966201e-05, 0.0003307162753862998, 0.0001694330212736881, 0.00029589278268394074, 0.00021287169034950472, 0.00034821901768948376, 0.00015990014827667657]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2968636179739318e-05, 0.9980771063697577, 0.0002841256136830965, 9.876644471966201e-05, 0.0003307162753862998, 0.0001694330212736881, 0.00029589278268394074, 0.00021287169034950472, 0.00034821901768948376, 0.00015990014827667657]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.149593852984466e-05, 0.4995435067665471, 0.00014220655349735, 0.4995435067665471, 0.00016552545579583608, 8.480223127946675e-05, 0.00014809609131950967, 0.00010654354258789985, 0.0001742856820472581, 8.003097184861164e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.825917865362964e-06, 0.3331586443716899, 0.3331586443716899, 0.3331586443716899, 0.00011265076810500442, 5.766221132700963e-05, 0.00010066396297479856, 7.230478309760173e-05, 0.00011861994642033553, 5.43392951403499e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[5.870525886401434e-06, 0.2499152789117222, 0.2499152789117222, 0.2499152789117222, 8.450372999829096e-05, 4.3254671220173873e-05, 7.551196046751536e-05, 0.2499152789117222, 8.898144321015484e-05, 4.076202232866605e-05]
[-1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 789.
Rec Success! in episode: 789.
total combined:  66
-----
It has processed 790 episodes
----target item:  409
[2.4290512140450253e-05, 1.4647812599681744e-05, 0.0002893903462061965, 0.9981109462839592, 0.0003394706301654084, 0.00017586823136813085, 0.00030611779684519384, 0.0002173211484457017, 0.0003588706947876219, 0.00016307654348215428]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995333627802094, 7.330919586179611e-06, 0.0001448337314951994, 0.4995333627802094, 0.00016989785161959257, 8.801832035667977e-05, 0.00015320546581947268, 0.00010876462630783904, 0.00017960717256729675, 8.161635182892568e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.33315991301028486, 4.8893001220653504e-06, 9.659573710420304e-05, 0.33315991301028486, 0.00011331205818003126, 5.8703138044946185e-05, 0.33315991301028486, 7.253972635108928e-05, 0.00011978761469606186, 5.443339464696702e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.24992054667873773, 3.6677178485914344e-06, 0.24992054667873773, 0.24992054667873773, 8.500125741349957e-05, 4.4036271409091914e-05, 0.24992054667873773, 5.441581462122248e-05, 8.985890853338525e-05, 4.083331522339997e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.1999497333666761, 0.1999497333666761, 0.1999497333666761, 0.1999497333666761, 6.800552808292728e-05, 3.523135990106895e-05, 0.1999497333666761, 4.353554667288016e-05, 7.189190741074632e-05, 3.2668824552034615e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16664059854860866, 0.16664059854860866, 0.16664059854860866, 0.16664059854860866, 0.16664059854860866, 3.010268239003985e-05, 0.16664059854860866, 3.7222461735434484e-05, 6.131770181812106e-05, 2.7765862404422874e-05]
[1, 0, 0, 1, 1, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2178]
random_location_list [2178]
Random Combined Rec Success! in episode: 790.
Random Combined Rec Success! in episode: 790.
Rec Success! in episode: 790.
total combined:  67
-----
It has processed 791 episodes
----target item:  411
[2.6026390698540934e-05, 1.483914545089907e-05, 0.0003000699929835136, 0.0001047129773680417, 0.00035075878914729325, 0.9981177808815342, 0.0003172831525861474, 0.00022818621735089012, 0.0003707771642211077, 0.00016956528865926814]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 791.
Rec Success! in episode: 791.
total combined:  67
-----
It has processed 792 episodes
----target item:  1936
[2.553749504233456e-05, 1.4918057378409277e-05, 0.9982404694904684, 0.00010474010142877577, 0.00035309042190672003, 0.00018198022581466882, 0.00031555483989584727, 0.00022440108562497187, 0.00037090444862168236, 0.00016840383381804932]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.499566114488806, 7.465692073230604e-06, 0.499566114488806, 5.241683452149058e-05, 0.00017670292432162064, 9.107139722599443e-05, 0.0001579183674604678, 0.00011230077507272156, 0.0001856178945931986, 8.427713711951926e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331755260382588, 4.97909247964816e-06, 0.3331755260382588, 3.4958348671883974e-05, 0.000117848444992307, 6.0738228230029046e-05, 0.3331755260382588, 7.489673283314051e-05, 0.00012379410428284518, 5.620693373394019e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991215625153565, 0.24991215625153565, 0.24991215625153565, 2.6221962937878908e-05, 8.839712613085502e-05, 4.5559233489801436e-05, 0.24991215625153565, 5.617940855708583e-05, 9.285691509345948e-05, 4.2160347648473936e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.1999510642558018, 0.1999510642558018, 0.1999510642558018, 2.0979809365607284e-05, 7.072524887196318e-05, 0.1999510642558018, 0.1999510642558018, 4.494832383801573e-05, 7.429346085014127e-05, 3.37318780652758e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([7], dtype=torch.int32)
[0.1666389241632462, 0.1666389241632462, 0.1666389241632462, 1.7484542404646656e-05, 5.89423188471967e-05, 0.1666389241632462, 0.1666389241632462, 0.1666389241632462, 6.191606148489188e-05, 2.8112097786147497e-05]
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0]
[0, 1, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 792.
Rec Success! in episode: 792.
total combined:  67
-----
It has processed 793 episodes
----target item:  1936
[2.3824747288915834e-05, 0.9979256102799584, 0.00030571774604068653, 0.00010610163948127813, 0.000358631990604023, 0.00018477749327613411, 0.0003202679818329683, 0.00022785275085411327, 0.00037636741703275415, 0.00017084795363084084]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 793.
Rec Success! in episode: 793.
total combined:  67
-----
It has processed 794 episodes
----target item:  251
[2.2121992171580426e-05, 0.9980863475674524, 0.00028226504016163435, 9.803617575008292e-05, 0.0003272918640832065, 0.00016997177301430623, 0.00029647674874331404, 0.0002129021216233879, 0.00034620459325864286, 0.00015838212374129278]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 794.
Rec Success! in episode: 794.
total combined:  67
-----
It has processed 795 episodes
----target item:  1306
[2.359651311644631e-05, 0.9979830803111286, 0.0002960086490191976, 0.00010338348543268058, 0.00034481005362523975, 0.0001796913456564022, 0.0003127164717159293, 0.00022482225519701696, 0.0003651297435361537, 0.00016676117157232953]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.359651311644631e-05, 0.9979830803111286, 0.0002960086490191976, 0.00010338348543268058, 0.00034481005362523975, 0.0001796913456564022, 0.0003127164717159293, 0.00022482225519701696, 0.0003651297435361537, 0.00016676117157232953]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1810777773024723e-05, 0.4995211082512927, 0.0001481613980508971, 0.4995211082512927, 0.00017258799625076847, 8.994102394748909e-05, 0.00015652417521074195, 0.00011253042690919912, 0.00018275862361296583, 8.346907565920295e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.877144774295277e-06, 0.33315334206852654, 0.33315334206852654, 0.33315334206852654, 0.0001151067828807914, 5.9985758804205304e-05, 0.00010439309015094727, 7.505165885870393e-05, 0.00012189003676271757, 5.56693221885728e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990021781875169, 0.24990021781875169, 0.24990021781875169, 0.24990021781875169, 8.634225289689213e-05, 4.499565905033188e-05, 7.83058510099781e-05, 5.629667641932568e-05, 9.143041023635706e-05, 4.175787538065606e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 795.
Rec Success! in episode: 795.
total combined:  67
-----
It has processed 796 episodes
----target item:  1089
[2.440977886304004e-05, 1.4431100866594927e-05, 0.9983305399271645, 0.00010029092392156837, 0.0003341515807926792, 0.0001732246228376806, 0.0002985321456936462, 0.0002125422036052292, 0.00035173368269166884, 0.00016014403356352688]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.4995883888186215, 7.2216667150612925e-06, 0.4995883888186215, 5.01879679036592e-05, 0.00016721741266333433, 8.668572858995584e-05, 0.00014939259865628848, 0.00010636118280308518, 0.00017601591537206833, 8.013989005360356e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.33315194919890156, 0.33315194919890156, 0.33315194919890156, 3.346799026489454e-05, 0.00011150941097834908, 5.7806626602676343e-05, 9.962288266131255e-05, 7.092725964616684e-05, 0.00011737671773137044, 5.344151541047291e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.24991663314487766, 0.24991663314487766, 0.24991663314487766, 2.510628398014957e-05, 8.364968784570853e-05, 4.3364109166231536e-05, 0.24991663314487766, 5.3206658317882675e-05, 8.805109553030788e-05, 4.0089585649014475e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 796.
Rec Success! in episode: 796.
total combined:  67
-----
It has processed 797 episodes
----target item:  227
[2.2483951636926224e-05, 0.9979904939643651, 0.0002958262341198363, 0.00010114980460592521, 0.00034549575972273863, 0.00017915699038110458, 0.0003127624668639966, 0.00022224633377963783, 0.00036397411219914855, 0.0001664103823254972]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.2483951636926224e-05, 0.9979904939643651, 0.0002958262341198363, 0.00010114980460592521, 0.00034549575972273863, 0.00017915699038110458, 0.0003127624668639966, 0.00022224633377963783, 0.00036397411219914855, 0.0001664103823254972]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1253852323028514e-05, 0.49952240692493616, 0.0001480693788094907, 0.49952240692493616, 0.00017293037811763381, 8.967312974805997e-05, 0.00015654644126225783, 0.0001112405621609172, 0.0001821793150171803, 8.329309268901649e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.50569890468217e-06, 0.3331538992073545, 0.3331538992073545, 0.3331538992073545, 0.00011533502594198816, 5.980703250851877e-05, 0.00010440784355323932, 7.419132058974233e-05, 0.0001215035568204633, 5.555189961789917e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990046166692262, 0.24990046166692262, 0.24990046166692262, 0.24990046166692262, 8.651339905624336e-05, 4.486156419110449e-05, 7.831686307043036e-05, 5.565129302453616e-05, 9.114044594960171e-05, 4.166976701763629e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 797.
Rec Success! in episode: 797.
total combined:  67
-----
It has processed 798 episodes
----target item:  599
[0.9979706999874388, 1.456824546379111e-05, 0.00030087842458940273, 0.00010415029030889006, 0.00035287078544400343, 0.00018133343603706867, 0.0003143159191146716, 0.00022436094552978953, 0.0003683455725264099, 0.00016847639354693888]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 798.
Rec Success! in episode: 798.
total combined:  67
-----
It has processed 799 episodes
----target item:  223
[2.298896361499801e-05, 0.9980327703173535, 0.0002914701478979831, 0.00010077924412794765, 0.00033951977743740697, 0.00017399203230962496, 0.00030342166059243623, 0.00021633272173711852, 0.00035699541822370456, 0.0001617297167049949]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 799.
Rec Success! in episode: 799.
total combined:  67
-----
It has processed 800 episodes
----target item:  1947
[2.344179324363412e-05, 0.9979935233531373, 0.0002962351655447527, 0.00010401763094294725, 0.0003446567572037355, 0.00018044125556864347, 0.00030717019001289827, 0.00022019873760377519, 0.0003636013382064848, 0.00016671377853581232]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 800.
Rec Success! in episode: 800.
total combined:  67
-----
It has processed 801 episodes
----target item:  544
[0.9979144326600139, 1.498293670857011e-05, 0.00030795007538064495, 0.00010861667996467195, 0.0003602736551422691, 0.00018687976309699495, 0.0003236014928835504, 0.00023174677926451147, 0.0003793019514191766, 0.00017221400612599748]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 801.
Rec Success! in episode: 801.
total combined:  67
-----
It has processed 802 episodes
----target item:  193
[2.5874360708565085e-05, 1.524541999631436e-05, 0.0003115797221140151, 0.00010715051879616918, 0.9982370182417163, 0.00018731709503554977, 0.0003258136495414724, 0.00023228479747086265, 0.0003817163652404096, 0.00017599982938022306]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2950613776526694e-05, 7.630625098607647e-06, 0.4996367727222983, 5.363088968703671e-05, 0.4996367727222983, 9.375579860194668e-05, 0.0001630759803443365, 0.00011626299610208587, 0.0001910563617044934, 8.809129008869984e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317473712827, 5.088359484633106e-06, 0.33317473712827, 3.5762895265047115e-05, 0.33317473712827, 6.251954471496916e-05, 0.00010874459177038556, 7.752810697459859e-05, 0.0001274028585621304, 5.8742258418408235e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991173286607965, 0.24991173286607965, 0.24991173286607965, 2.6825464634658468e-05, 0.24991173286607965, 4.6895415577985494e-05, 8.156845745086816e-05, 5.815321931923492e-05, 9.556387567012946e-05, 4.406210302841662e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 802.
Rec Success! in episode: 802.
total combined:  67
-----
It has processed 803 episodes
----target item:  1195
[2.546439713059943e-05, 1.5293869801231072e-05, 0.0003088569959783222, 0.9979903172052244, 0.000359423014182843, 0.00018772979406572128, 0.0003245565661100141, 0.00023147071677340417, 0.00038173237861550675, 0.00017515506211786852]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.4995034401143604, 7.654724145790598e-06, 0.00015458580041797574, 0.4995034401143604, 0.00017989456304883552, 9.396050876564288e-05, 0.0001624435813542252, 0.00011585324759245761, 0.00019106060753721002, 8.766673841719093e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([6], dtype=torch.int32)
[0.3331486574897803, 5.10539241139338e-06, 0.00010310249688058384, 0.3331486574897803, 0.00011998242125361332, 6.266787140677939e-05, 0.3331486574897803, 7.726944561667446e-05, 0.00012742972277754566, 5.8470180312488405e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[0.2499154333038189, 3.829870923968966e-06, 0.2499154333038189, 0.2499154333038189, 9.000624232549381e-05, 4.701105012657514e-05, 0.2499154333038189, 5.796459492870521e-05, 9.559292426298543e-05, 4.386210215659122e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.19994648630945072, 0.19994648630945072, 0.19994648630945072, 0.19994648630945072, 7.20100862159298e-05, 3.7611499883238796e-05, 0.19994648630945072, 4.637495545245349e-05, 7.647974784811862e-05, 3.509216334669069e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([4], dtype=torch.int32)
[0.16663950294101512, 0.16663950294101512, 0.16663950294101512, 0.16663950294101512, 0.16663950294101512, 3.1346195480068894e-05, 0.16663950294101512, 3.8649839105191115e-05, 6.37397905894697e-05, 2.9246528734528932e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([5], dtype=torch.int32)
[0.14284102333544987, 0.14284102333544987, 0.14284102333544987, 0.14284102333544987, 0.14284102333544987, 0.14284102333544987, 0.14284102333544987, 3.3130095038090465e-05, 5.4636846331748095e-05, 2.506971048112455e-05]
[1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 803.
Rec Success! in episode: 803.
total combined:  67
-----
It has processed 804 episodes
----target item:  1911
[0.9979133140361115, 1.5059306173643306e-05, 0.00031062105362178385, 0.00010790429728797313, 0.00035919986016551573, 0.0001864794927242004, 0.000324273236780599, 0.00023057257611768306, 0.00037940558611639693, 0.0001731705549005482]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.9979133140361115, 1.5059306173643306e-05, 0.00031062105362178385, 0.00010790429728797313, 0.00035919986016551573, 0.0001864794927242004, 0.000324273236780599, 0.00023057257611768306, 0.00037940558611639693, 0.0001731705549005482]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995047611601826, 7.537924414576511e-06, 0.0001554811355037786, 0.4995047611601826, 0.0001797972206975226, 9.334217027101714e-05, 0.00016231472554826642, 0.00011541293010505276, 0.00018991118167309266, 8.668039142169863e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331476980146753, 5.0274639238513116e-06, 0.3331476980146753, 0.3331476980146753, 0.00011991683531842773, 6.225512061437796e-05, 0.00010825678026509924, 7.697534633367956e-05, 0.00012666240228558802, 5.781200723307907e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 804.
Rec Success! in episode: 804.
total combined:  67
-----
It has processed 805 episodes
----target item:  1720
[2.3811189345438484e-05, 1.4163218489369348e-05, 0.0002745732073247846, 9.614860198587704e-05, 0.9984420909145714, 0.0001657601435744925, 0.000288033589919294, 0.00020438608134314525, 0.0003364142643887197, 0.00015461878905759073]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.1916513072317436e-05, 7.088103656904915e-06, 0.49967887179960363, 4.811838904087514e-05, 0.49967887179960363, 8.295607956068186e-05, 0.00014414887008562318, 0.0001022867600098232, 0.00016836139182901488, 7.738029353765329e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331932266948786, 4.7264518511382675e-06, 0.3331932266948786, 3.2086050086821766e-05, 0.3331932266948786, 5.5316334915729336e-05, 9.612058835962124e-05, 6.820631717545577e-05, 0.00011226585425218441, 5.1598318723285296e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24992206776021592, 0.24992206776021592, 0.24992206776021592, 2.4067151855099843e-05, 0.24992206776021592, 4.1491758221471075e-05, 7.20982729314717e-05, 5.116029515932848e-05, 8.420853782621091e-05, 3.870294314260842e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 805.
Rec Success! in episode: 805.
total combined:  67
-----
It has processed 806 episodes
----target item:  40
[2.3004733985702473e-05, 0.9981008199752581, 0.00027943358721482423, 9.807922770326401e-05, 0.0003265306864100417, 0.0001674268207631722, 0.00029352649178275797, 0.00021075961408491, 0.000344136890547451, 0.00015628197224963492]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2121]
random_location_list [2121]
Random Combined Rec Success! in episode: 806.
Random Combined Rec Success! in episode: 806.
Rec Success! in episode: 806.
total combined:  68
-----
It has processed 807 episodes
----target item:  899
[2.5832156621862716e-05, 1.5408767682301648e-05, 0.00029368377532583786, 0.00010369533335211878, 0.9983242037401122, 0.0001803428904667584, 0.00030888655453199055, 0.00022112790148767655, 0.000363010859706756, 0.00016380802071230417]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2928809827348378e-05, 7.711978134634908e-06, 0.49965413128809816, 5.18987734751651e-05, 0.49965413128809816, 9.026032819055076e-05, 0.0001545955136548337, 0.00011067293481161328, 0.00018168434169521787, 8.198474401441634e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 807.
Rec Success! in episode: 807.
total combined:  68
-----
It has processed 808 episodes
----target item:  499
[2.6199629384543805e-05, 1.5367851574972095e-05, 0.0002975064926398818, 0.00010232177076783385, 0.9983095841174423, 0.00017945681737029104, 0.0003150240020790311, 0.00022315091005475668, 0.0003656511341861352, 0.00016573727450005173]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.392987861911495e-05, 8.170197303613492e-06, 0.49963495319445095, 5.334937866400424e-05, 0.49963495319445095, 9.419495022468096e-05, 0.0001649936359768796, 0.00011712814905118366, 0.0001913916315370436, 8.693578972149444e-05]
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33317414561827197, 5.448174689861484e-06, 0.33317414561827197, 3.557524056714191e-05, 0.33317414561827197, 6.281250313256164e-05, 0.00011002355489259547, 7.810516605868866e-05, 0.00012762666604516855, 5.79718397980775e-05]
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24991146751131355, 0.24991146751131355, 0.24991146751131355, 2.6684725372984843e-05, 0.24991146751131355, 4.711519498845702e-05, 8.252785645475411e-05, 5.858610857610086e-05, 9.573182020392401e-05, 4.348424914959481e-05]
[1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2183]
random_location_list [2183]
Random Combined Rec Success! in episode: 808.
Random Combined Rec Success! in episode: 808.
Rec Success! in episode: 808.
total combined:  69
-----
It has processed 809 episodes
----target item:  157
[2.4930843028154768e-05, 1.4640070232598971e-05, 0.00028367142826521224, 9.918953073222222e-05, 0.9983853277373457, 0.00017169860848482955, 0.00029819871477232787, 0.00021272266763521056, 0.00034924702218400497, 0.0001603733773198882]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2477264582327284e-05, 7.326989688623903e-06, 0.49966693365420467, 4.9641884044802025e-05, 0.49966693365420467, 8.59308674024091e-05, 0.00014924101275365766, 0.00010646238491596803, 0.0001747894162848244, 8.026287191820461e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 1, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.3331880431023686, 4.885785293675873e-06, 0.3331880431023686, 3.3102214869092926e-05, 0.3331880431023686, 5.730044480332179e-05, 9.951693346276005e-05, 7.099127699875167e-05, 0.00011655312698208173, 5.352091048456277e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499191812270438, 0.2499191812270438, 0.2499191812270438, 2.4829457743607025e-05, 0.2499191812270438, 4.2980174546034885e-05, 7.464610763837575e-05, 5.324945534236717e-05, 8.74246920555429e-05, 4.014520449858467e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 809.
Rec Success! in episode: 809.
total combined:  69
-----
It has processed 810 episodes
----target item:  264
[0.9979673489008705, 1.5028231654367019e-05, 0.00029925622745795375, 0.00010673710527024321, 0.00035137194903800444, 0.00018041172360560385, 0.0003153571503683088, 0.00022611071985875652, 0.0003690358125271682, 0.00016934217934907772]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 810.
Rec Success! in episode: 810.
total combined:  69
-----
It has processed 811 episodes
----target item:  1048
[2.5146560019598646e-05, 1.4961058863846544e-05, 0.0002887960783771825, 0.00010116300704137, 0.9983542608790507, 0.0001750928375807439, 0.0003038658846130335, 0.0002176672518004988, 0.00035599672450024986, 0.00016304971815302077]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2585453511207779e-05, 7.487772111280174e-06, 0.49966043578989844, 5.063047674039147e-05, 0.49966043578989844, 8.763118159304709e-05, 0.00015208004440602602, 0.0001089389990643841, 0.00017817070099640798, 8.160379178030912e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 811.
Rec Success! in episode: 811.
total combined:  69
-----
It has processed 812 episodes
----target item:  1679
[2.3422252333301864e-05, 0.9980444290681751, 0.0002873110185906078, 9.860531950881491e-05, 0.0003372290400790379, 0.00017382086273274547, 0.000302473858051556, 0.00021598631557433868, 0.0003554044104858699, 0.0001613178544686118]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[2.3422252333301864e-05, 0.9980444290681751, 0.0002873110185906078, 9.860531950881491e-05, 0.0003372290400790379, 0.00017382086273274547, 0.000302473858051556, 0.00021598631557433868, 0.0003554044104858699, 0.0001613178544686118]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[1.1723166892161082e-05, 0.49953528128985203, 0.00014380320786253233, 0.49953528128985203, 0.00016878788006689213, 8.699978781537344e-05, 0.00015139242238512574, 0.00010810419031737916, 0.000177884908720417, 8.07418562360903e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[7.818616461097452e-06, 0.33315867709802777, 0.33315867709802777, 0.33315867709802777, 0.00011257092129321982, 5.802339754969325e-05, 0.000100969242921659, 7.209870930816896e-05, 0.0001186380683902286, 5.3849749992826875e-05]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([0], dtype=torch.int32)
[0.24990320861173135, 0.24990320861173135, 0.24990320861173135, 0.24990320861173135, 8.443974706766188e-05, 4.3523504621060503e-05, 7.573729730531848e-05, 5.4081433357278115e-05, 8.899073022040063e-05, 4.039284050280754e-05]
[-1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.24990320861173135, 0.24990320861173135, 0.24990320861173135, 0.24990320861173135, 8.443974706766188e-05, 4.3523504621060503e-05, 7.573729730531848e-05, 5.4081433357278115e-05, 8.899073022040063e-05, 4.039284050280754e-05]
[-1, 0, 0, 1, -1, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 812.
Rec Success! in episode: 812.
total combined:  69
-----
It has processed 813 episodes
----target item:  378
[2.4910137196445418e-05, 1.4721123538790414e-05, 0.0002826838430631449, 9.82015188253317e-05, 0.00033173148592860046, 0.00017114446678627, 0.00029797545090099755, 0.00021278174601850003, 0.9984050096093919, 0.0001608406183500609]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.246677286731771e-05, 7.367478631792229e-06, 0.4996716150631466, 4.914690034688894e-05, 0.00016602161021416615, 8.565264727755443e-05, 0.00014912773210054434, 0.00010649085057237079, 0.4996716150631466, 8.049588169651957e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([0], dtype=torch.int32)
[0.33319012232400175, 4.91276877161833e-06, 0.33319012232400175, 3.277204717013194e-05, 0.0001107062297479016, 5.7114743290303434e-05, 9.944108450947721e-05, 7.101003630976951e-05, 0.33319012232400175, 5.367611819545176e-05]
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.2499203561035295, 0.2499203561035295, 0.2499203561035295, 2.458176623566441e-05, 8.303889733732855e-05, 4.284081677545593e-05, 7.458909969654717e-05, 5.326344441929376e-05, 0.2499203561035295, 4.026156141753093e-05]
[0, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
star_location_list:  [2177]
random_location_list [2177]
Random Combined Rec Success! in episode: 813.
Random Combined Rec Success! in episode: 813.
Rec Success! in episode: 813.
total combined:  70
-----
It has processed 814 episodes
----target item:  1793
[0.9980226438387813, 1.4809996597379787e-05, 0.0002933861322259606, 0.00010133705063506326, 0.00034086428267705615, 0.0001762527906962568, 0.0003082989457828175, 0.00021774489813139905, 0.0003602484629313114, 0.00016441360154165102]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 814.
Rec Success! in episode: 814.
total combined:  70
-----
It has processed 815 episodes
----target item:  334
[0.9980519923373753, 1.4310522759791684e-05, 0.00028692164572444737, 0.00010017525191159317, 0.0003360946915519476, 0.00017371488304254335, 0.0003036130814987023, 0.0002187765028861914, 0.0003532506953876251, 0.0001611503878619305]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 815.
Rec Success! in episode: 815.
total combined:  70
-----
It has processed 816 episodes
----target item:  1679
[2.3262124946228716e-05, 0.9980564399416847, 0.0002853849450967624, 0.00010071751550883448, 0.0003351875539617735, 0.00017273162403738088, 0.00029808824454510266, 0.00021499590740314904, 0.00035221394186771754, 0.00016097820094823092]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 816.
Rec Success! in episode: 816.
total combined:  70
-----
It has processed 817 episodes
----target item:  1335
[0.9980219531147201, 1.456749118503372e-05, 0.0002935587466650042, 0.00010133315975185736, 0.00034201122313101185, 0.00017765200088628571, 0.0003064683083025155, 0.00021760653423115626, 0.0003591479195951824, 0.0001657015015316493]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 817.
Rec Success! in episode: 817.
total combined:  70
-----
It has processed 818 episodes
----target item:  1197
[2.4199275877478197e-05, 1.39600314049929e-05, 0.0002862546672745657, 9.94699594409962e-05, 0.9983812110896391, 0.00017225277498175728, 0.0002982605434520159, 0.0002138853756200703, 0.00035063057838850446, 0.0001598757039205431]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[1.2111174095953662e-05, 6.986670658529995e-06, 0.49966654881971373, 4.978239853980688e-05, 0.49966654881971373, 8.620850296833736e-05, 0.00014927245699376492, 0.00010704465017170008, 0.00017548244004194713, 8.001406710259872e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 818.
Rec Success! in episode: 818.
total combined:  70
-----
It has processed 819 episodes
----target item:  1277
[2.330134644733661e-05, 0.9979798898129256, 0.00029683178031695716, 0.00010438877843351306, 0.00034823866961923117, 0.00017988778298520528, 0.0003126486592833954, 0.00022046998240335858, 0.00036676433156492135, 0.00016757885602021713]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 819.
Rec Success! in episode: 819.
total combined:  70
-----
It has processed 820 episodes
----target item:  622
[2.5268158100979712e-05, 1.5109413260264629e-05, 0.0002852694284604814, 9.989922917376425e-05, 0.00033201498406076885, 0.00017133390507636625, 0.9983463617373521, 0.0002132564894717067, 0.00035007270597539066, 0.0001614139490681179]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([2], dtype=torch.int32)
[1.2646339092555317e-05, 7.562037676638157e-06, 0.49965757582702186, 4.999808542306586e-05, 0.00016616858480393288, 8.57500832861815e-05, 0.49965757582702186, 0.00010673171620857436, 0.00017520620731914584, 8.07852921461943e-05]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 1, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 820.
Rec Success! in episode: 820.
total combined:  70
-----
It has processed 821 episodes
----target item:  87
[0.998093976461213, 1.4030975505270273e-05, 0.00028367303545301543, 9.753892052234743e-05, 0.0003294970434839909, 0.00016997591416890998, 0.0002957999059858923, 0.0002093330493164499, 0.0003476505804230022, 0.00015852411392811654]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
[0.998093976461213, 1.4030975505270273e-05, 0.00028367303545301543, 9.753892052234743e-05, 0.0003294970434839909, 0.00016997591416890998, 0.0002957999059858923, 0.0002093330493164499, 0.0003476505804230022, 0.00015852411392811654]
[-1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([3], dtype=torch.int32)
[0.4995454022142275, 7.059804827045412e-06, 0.00014263363765840338, 0.4995454022142275, 0.0001657452839702461, 8.563244815561237e-05, 0.0001486664319788143, 0.00010523478289896414, 0.0001747473523270814, 7.947582972860511e-05]
[-1, 1, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([2], dtype=torch.int32)
[0.3331667118341926, 4.720085336344066e-06, 0.3331667118341926, 0.3331667118341926, 0.00010802555815767898, 5.57570036093313e-05, 9.685753185390645e-05, 6.867560001624634e-05, 0.00011397919410791384, 5.184952434062655e-05]
[-1, 1, 1, 0, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([1], dtype=torch.int32)
[0.24990714849074042, 0.24990714849074042, 0.24990714849074042, 0.24990714849074042, 8.102958142091188e-05, 4.1823127237665e-05, 7.265248518437562e-05, 5.151331979256097e-05, 8.549538226663268e-05, 3.889214113628442e-05]
[-1, 1, 1, 1, 0, 0, 0, 0, 0, 0]
[1, 0, 0, 0, 0, 0, 0, 0]
action is: tensor([10], dtype=torch.int32)
gamma: 0
[0]
star_location_list:  [2135]
random_location_list [2135]
Random Combined Rec Success! in episode: 821.
Random Combined Rec Success! in episode: 821.
Rec Success! in episode: 821.
total combined:  71
-----
It has processed 822 episodes
----target item:  1423
[0.9980206182995092, 1.4933307889368181e-05, 0.000292969877964753, 0.00010274490451103238, 0.0003427453002383513, 0.00017432906255822358, 0.00030818233807449293, 0.0002188981303789994, 0.0003610614549697975, 0.00016351732390604306]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 822.
Rec Success! in episode: 822.
total combined:  71
-----
It has processed 823 episodes
----target item:  1357
[0.9979729652092247, 1.552018287222142e-05, 0.0003000314324467427, 0.00010376098584310185, 0.0003483298502706982, 0.00018180497311583927, 0.00031450048176214087, 0.00022557032925160837, 0.00036815013238245263, 0.0001693664228305581]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 823.
Rec Success! in episode: 823.
total combined:  71
-----
It has processed 824 episodes
----target item:  487
[0.9980757312733652, 1.4393987595907844e-05, 0.000282381616005258, 9.82546134933812e-05, 0.0003327041846174481, 0.00017373439389970022, 0.00029834510144106035, 0.00021469676627795396, 0.00035025177522529714, 0.00015950628807875924]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 824.
Rec Success! in episode: 824.
total combined:  71
-----
It has processed 825 episodes
----target item:  909
[0.9980815817631898, 1.4677187998705369e-05, 0.000283497527944754, 9.936288519281677e-05, 0.0003336521053808667, 0.00017216456926860894, 0.00029507900400175456, 0.0002109272373325988, 0.00034841328688165157, 0.0001606444328081569]
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
[0, 0, 0, 0, 0, 0, 0, 1]
action is: tensor([10], dtype=torch.int32)
gamma: 0
Independent Rec Success! in episode: 825.
Rec Success! in episode: 825.
total combined:  71
-----
It has processed 826 episodes
Traceback (most recent call last):
  File "/home/workstation/mushi/CART-master/Test_transE.py", line 388, in <module>
    main()
  File "/home/workstation/mushi/CART-master/Test_transE.py", line 172, in main
    items = the_valid_list_item[epi_count]  #0 18 10 3 
IndexError: list index out of range