Try some training on the bigger sphere which has a slightly different…

… agent sensor config for the different radius
plaidpants · Feb 20, 2022 · 56de1b7 · 56de1b7
1 parent 1940e1b
commit 56de1b7
Show file tree

Hide file tree

Showing 13 changed files with 113 additions and 0 deletions.
diff --git a/Assets/Demonstrations2.meta b/Assets/Demonstrations2.meta
diff --git a/Assets/Demonstrations2/RocketAI_9.demo b/Assets/Demonstrations2/RocketAI_9.demo
diff --git a/Assets/Demonstrations2/RocketAI_9.demo.meta b/Assets/Demonstrations2/RocketAI_9.demo.meta
diff --git a/Assets/RocketAI73-3499999.onnx b/Assets/RocketAI73-3499999.onnx
diff --git a/Assets/RocketAI73-3499999.onnx.meta b/Assets/RocketAI73-3499999.onnx.meta
diff --git a/Assets/RocketAI73-5864266.onnx b/Assets/RocketAI73-5864266.onnx
diff --git a/Assets/RocketAI73-5864266.onnx.meta b/Assets/RocketAI73-5864266.onnx.meta
diff --git a/Assets/RocketAIDemo2.yaml b/Assets/RocketAIDemo2.yaml
@@ -0,0 +1,49 @@
+behaviors:
+  RocketAI:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 16384
+      learning_rate: 0.0003
+      beta: 0.001
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      curiosity:
+        gamma: 0.99
+        strength: 0.02
+        network_settings:
+          hidden_units: 256
+        learning_rate: 0.0003
+      gail:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+        learning_rate: 0.0003
+        use_actions: false
+        use_vail: false
+        demo_path: 'J:\Unity Projects\RocksRocketsAndRayguns\Assets\Demonstrations2\'
+    keep_checkpoints: 5
+    checkpoint_interval: 500000
+    max_steps: 10000000
+    time_horizon: 2000
+    summary_freq: 10000
+    behavioral_cloning:
+      demo_path: 'J:\Unity Projects\RocksRocketsAndRayguns\Assets\Demonstrations2\'
+      steps: 1000
+      strength: 1.0
+      samples_per_update: 0
diff --git a/Assets/RocketAIDemo2.yaml.meta b/Assets/RocketAIDemo2.yaml.meta
diff --git a/Assets/RocketSphereAI1.prefab b/Assets/RocketSphereAI1.prefab
diff --git a/Assets/RocketSphereAI2.prefab b/Assets/RocketSphereAI2.prefab
diff --git a/Assets/Training3.unity b/Assets/Training3.unity
diff --git a/Assets/Training3.unity.meta b/Assets/Training3.unity.meta