Push agent to the Hub

README.md

@@ -0,0 +1,54 @@
+---
+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: 79.47 +/- 57.46
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'env_id': 'LunarLander-v2'
+'seed': 1
+'num_envs': 16
+'pi_hidden_layers': (64
+64)
+'v_hidden_layers': (64
+64)
+'learning_rate': 0.0003
+'anneal_lr': True
+'total_timesteps': 1000000
+'num_steps': 1024
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 256
+'num_epochs': 4
+'norm_advantage': True
+'clip_coef': 0.2
+'clip_vloss': True
+'vf_coef': 0.5
+'ent_coef': 0.01
+'max_grad_norm': 0.5
+'target_kl': None}
+  ```
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d237aadc03c4a69843d7bc5a7747d7777ab439ef09288af720bfe5fadc0ee2c5
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 79.46508621838886, "std_reward": 57.46079809014783, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T01:15:29.426508"}