Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 236.60 +/- 88.78
+      value: -197.79 +/- 110.40
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
     
   # Hyperparameters
   ```python
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'CartPole-v1'
+'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4

logs/events.out.tfevents.1682687161.66e8e241bbfe.14205.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f5e7d71f0aa50c6da9ef9977d688442a365bb904fe7b52d52f54f86e5fcceb
+size 109960

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2696e0cd90c2a51c12b41eb83e89a403053d0d874e11feec409c33eb1f196a3a
-size 40037
+oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 236.6, "std_reward": 88.77860102524707, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-28T12:59:03.067864"}
+{"env_id": "LunarLander-v2", "mean_reward": -197.79021866578432, "std_reward": 110.3987167187933, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-28T13:06:51.584570"}