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: -56.94 +/- 54.20
+      value: -55.89 +/- 37.85
       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

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": -56.9354474881085, "std_reward": 54.20333751769629, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-13T21:17:19.062586"}
+{"env_id": "LunarLander-v2", "mean_reward": -55.89419597242971, "std_reward": 37.845996085227654, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-13T21:17:49.023909"}