@@ -118,7 +118,7 @@ def _check_param_consistency(self, transition_probs, rewards):
118
118
for action in transition_probs [state ]:
119
119
assert isinstance (transition_probs [state ][action ], dict ), \
120
120
"transition_probs for %s, %s should be a a dictionary but is instead %s" % (
121
- state , action , type (transition_probs [state , action ]))
121
+ state , action , type (transition_probs [state ][ action ]))
122
122
next_state_probs = transition_probs [state ][action ]
123
123
assert len (next_state_probs ) != 0 , "from state %s action %s leads to no next states" % (state , action )
124
124
sum_probs = sum (next_state_probs .values ())
@@ -132,7 +132,7 @@ def _check_param_consistency(self, transition_probs, rewards):
132
132
for action in rewards [state ]:
133
133
assert isinstance (rewards [state ][action ], dict ), \
134
134
"rewards for %s, %s should be a a dictionary but is instead %s" % (
135
- state , action , type (transition_probs [state , action ]))
135
+ state , action , type (transition_probs [state ][ action ]))
136
136
msg = "The Enrichment Center once again reminds you that Android Hell is a real place where" \
137
137
" you will be sent at the first sign of defiance."
138
138
assert None not in transition_probs , "please do not use None as a state identifier. " + msg
0 commit comments