Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 294.45 +/- 15.95
+      value: 285.02 +/- 19.43
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca43fc3ba377f809452660bc01cf4cdb897f4b99761a067927f0f296048ca9ce
+oid sha256:39c7de456ac1f515382fecd4498bc15cd3b32a3d43ffff75ec6892b18845f871
 size 151639

results.json

@@ -1 +1 @@
-{"mean_reward": 294.450299, "std_reward": 15.949156446023723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-26T19:21:30.047255"}
+{"mean_reward": 285.0206271, "std_reward": 19.429255220562563, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-26T19:24:50.274042"}