Update rllib_config.yaml hyperparameters

examples/rllib_config.yaml

@@ -10,39 +10,44 @@ algorithm: PPO
 # Set to false if you have a single policy name for all agents set in AIControllers
 env_is_multiagent: false
 
-checkpoint_frequency: 10
+checkpoint_frequency: 20
 
 # You can set one or more stopping criteria
 stop:
     #episode_reward_mean: 0
     #training_iteration: 1000
     #timesteps_total: 10000
-    time_total_s: 1200
+    time_total_s: 10000000
 
 config:
     env: godot
     env_config:
-        env_path: null # Set your env path here (exported executable from Godot) - e.g. 'env_path.exe' on Windows
+        env_path: null # Set your env path here (exported executable from Godot) - e.g. env_path: 'env_path.exe' on Windows
         action_repeat: null # Doesn't need to be set here, you can set this in sync node in Godot editor as well
         show_window: true # Displays game window while training. Might be faster when false in some cases, turning off also reduces GPU usage if you don't need rendering.
-        speedup: 20 # Speeds up Godot physics
+        speedup: 30 # Speeds up Godot physics
 
     framework: torch # ONNX models exported with torch are compatible with the current Godot RL Agents Plugin
+
     lr: 0.0003
     lambda: 0.95
     gamma: 0.99
 
-    vf_clip_param: 10
     vf_loss_coeff: 0.5
-    clip_param: 0.2
+    vf_clip_param: .inf
+    #clip_param: 0.2
     entropy_coeff: 0.0001
     entropy_coeff_schedule: null
+    #grad_clip: 0.5
+
+    normalize_actions: False
+    clip_actions: True # During onnx inference we simply clip the actions to [-1.0, 1.0] range, set here to match
 
-    rollout_fragment_length: 64
-    sgd_minibatch_size: 64
-    num_workers: 1
-    num_envs_per_worker: 1
-    train_batch_size: 512
+    rollout_fragment_length: 32
+    sgd_minibatch_size: 128
+    num_workers: 4
+    num_envs_per_worker: 16
+    train_batch_size: 2048
 
     num_sgd_iter: 4
     batch_mode: truncate_episodes