Push agent to the Hub

README.md

@@ -0,0 +1,51 @@
+---
+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: 54.42 +/- 114.62
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'batch_size': 512
+'learning_rate': 0.00025
+'gamma': 0.99
+'seed': 42
+'device': 'cuda'
+'ent_coef': 0.01
+'clip_coef': 0.2
+'clip_vloss': True
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'num_envs': 4
+'num_steps': 128
+'anneal_lr': True
+'num_minibatches': 4
+'update_epochs': 4
+'norm_adv': True
+'gae_lambda': 0.95
+'env_id': 'LunarLander-v2'}
+  ```
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3cd01a6fc41e74024d884871d7ecd42e5f78c5b4d7a36646e26a52aae111a6
+size 43026

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 54.421640837474364, "std_reward": 114.62386509067649, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-15T19:26:17.794294"}