Create README.md

README.md

@@ -0,0 +1,39 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -101.69 +/- 95.52
+      name: mean_reward
+      verified: false
+---
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'max_frames': 400000
+'gamma': 0.95
+'PPO_epsilon': 0.2
+'max_t': 99
+'target_nets_update_freq': 50
+'lr': 0.00025
+'entropy_coef': 0.01
+'env_id': 'LunarLander-v2'}
+  ```
+