Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 257.39 +/- 23.04
+      value: 263.68 +/- 15.98
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee4b927f5f0d339871f24df7a52f694600daee13eedcf960a9e8076c5f395a37
+oid sha256:4ee7bd7a6d55033a2a3816acac9d155353387ead0ededc621a692b43add6776e
 size 150018

results.json

@@ -1 +1 @@
-{"mean_reward": 257.3877052, "std_reward": 23.04242573978996, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-03T02:45:36.844937"}
+{"mean_reward": 263.67939900000005, "std_reward": 15.980996784362313, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-03T02:51:10.728540"}