[CI] Better hyperparameters for Pyramids-SAC, WalkerStatic-SAC, and Reacher-PPO (#4154)

Author: Ervin T

config/ppo/Reacher.yaml

@@ -2,10 +2,10 @@ behaviors:
   Reacher:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 2024
-      buffer_size: 20240
+      batch_size: 512
+      buffer_size: 20480
       learning_rate: 0.0003
-      beta: 0.005
+      beta: 0.001
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3

config/sac/Pyramids.yaml

@@ -5,32 +5,32 @@ behaviors:
       learning_rate: 0.0003
       learning_rate_schedule: constant
       batch_size: 128
-      buffer_size: 500000
-      buffer_init_steps: 10000
+      buffer_size: 2000000
+      buffer_init_steps: 1000
       tau: 0.01
       steps_per_update: 10.0
       save_replay_buffer: false
       init_entcoef: 0.01
       reward_signal_steps_per_update: 10.0
     network_settings:
       normalize: false
-      hidden_units: 256
-      num_layers: 2
+      hidden_units: 512
+      num_layers: 3
       vis_encode_type: simple
     reward_signals:
       extrinsic:
-        gamma: 0.99
+        gamma: 0.995
         strength: 2.0
       gail:
         gamma: 0.99
-        strength: 0.02
+        strength: 0.01
         encoding_size: 128
         learning_rate: 0.0003
         use_actions: true
         use_vail: false
         demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
     keep_checkpoints: 5
-    max_steps: 10000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: true

config/sac/WalkerStatic.yaml

@@ -4,8 +4,8 @@ behaviors:
     hyperparameters:
       learning_rate: 0.0003
       learning_rate_schedule: constant
-      batch_size: 256
-      buffer_size: 500000
+      batch_size: 1024
+      buffer_size: 2000000
       buffer_init_steps: 0
       tau: 0.005
       steps_per_update: 30.0
@@ -14,15 +14,15 @@ behaviors:
       reward_signal_steps_per_update: 30.0
     network_settings:
       normalize: true
-      hidden_units: 512
-      num_layers: 4
+      hidden_units: 256
+      num_layers: 3
       vis_encode_type: simple
     reward_signals:
       extrinsic:
         gamma: 0.995
         strength: 1.0
     keep_checkpoints: 5
-    max_steps: 20000000
+    max_steps: 15000000
     time_horizon: 1000
     summary_freq: 30000
     threaded: true