Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 229.57 +/- 72.06
+      value: 263.30 +/- 16.31
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a23ab4906274373e8ea768ebf4e26166c8bd478e4b6a09857119347dc7a12e
+oid sha256:e8f80ae24b429612e7549ead1623ccb69204c4c5404346abfaa0900cfa7e99e6
 size 148068

results.json

@@ -1 +1 @@
-{"mean_reward": 229.573321154815, "std_reward": 72.06339969619901, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-07T22:07:28.772475"}
+{"mean_reward": 263.30483394576186, "std_reward": 16.30839899671451, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-07T22:15:43.781877"}