Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 263.64 +/- 13.32
+      value: 261.29 +/- 18.41
       name: mean_reward
       verified: false
 ---

done_lunar_lander_v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45d2e77bac6cc8cd3a9ff072bfbfec770f4e3d20297ccb0d67fa4ee6d080502b
+oid sha256:35a9a6272e94d4da67bc38597456824effe84e66c7c99c7df05d5a38d603e9b4
 size 150230

results.json

@@ -1 +1 @@
-{"mean_reward": 263.6417913, "std_reward": 13.323285654313686, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-19T09:29:22.868551"}
+{"mean_reward": 261.29160450000006, "std_reward": 18.405498667104006, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-19T09:40:02.715993"}