Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -40.42 +/- 24.70
+      value: -34.27 +/- 48.09
       name: mean_reward
       verified: false
 ---
@@ -25,7 +25,7 @@ model-index:
     # PPO Agent Playing LunarLander-v2
 
     This is a trained model of a PPO agent playing LunarLander-v2.
-    
+
     # Hyperparameters
     ```python
     {'exp_name': 'ppo'

logs/events.out.tfevents.1739702551.26e15e277ccc.5832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994fbf57dce8c83e703a560bdbaf00972c6054da212a527079d28db4fb286ac4
+size 302647

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -40.41602753659891, "std_reward": 24.697333142315664, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-16T10:16:07.589837"}
+{"env_id": "LunarLander-v2", "mean_reward": -34.26563472121725, "std_reward": 48.08901580502887, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-16T10:44:37.815212"}