Push agent to the Hub

README.md

@@ -17,14 +17,14 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -208.22 +/- 148.76
+      value: -256.71 +/- 117.21
       name: mean_reward
       verified: false
 ---
 # PPO Agent Playing LunarLander-v2
       This is a trained model of a PPO agent playing LunarLander-v2.
       ## Evaluation Results
-      - Mean Reward: -208.22 ± 148.76
+      - Mean Reward: -256.71 ± 117.21
       - Number of Evaluation Episodes: 10
       ## Hyperparameters
       ```python

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -208.22347884719656, "std_reward": 148.76047927764702, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:01:36.463806"}
+{"env_id": "LunarLander-v2", "mean_reward": -256.7072636878181, "std_reward": 117.20978945433933, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-16T04:03:25.286241"}