Update README.md

README.md

@@ -21,6 +21,42 @@
   ```
   mlagents-learn ./config/ppo/PyramidsRND.yaml --run-id="Pyramids-Training" --resume
   ```
+  ### Training hyperparameters
+  ```python
+  behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 4096
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          hidden_units: 128
+          num_layers: 3
+        learning_rate: 0.0001
+    keep_checkpoints: 5
+    max_steps: 900000
+    time_horizon: 256
+    summary_freq: 30000
+  ```
+
   ### Watch your Agent play
   You can watch your agent **playing directly in your browser:**.