Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 262.58 +/- 15.75
+      value: 264.12 +/- 15.25
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bfb2a536009e3c4565f1fd840352c1392fbb9851166187e837952c0d0bc432c
+oid sha256:60596ca95bb0a033228559ac0d50e51c76d18467dd423678398ddce16adc9bac
 size 150350

results.json

@@ -1 +1 @@
-{"mean_reward": 262.5836337, "std_reward": 15.745259889558533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-09-11T06:19:49.636494"}
+{"mean_reward": 264.11657990000003, "std_reward": 15.246895270158488, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-09-11T06:20:13.536000"}