feat:Uploaded PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 261.83 +/- 11.29
+      value: 256.79 +/- 29.50
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ce12c05c09d2a241406a2eb3025c9e4d7bbf1fe922035f4bf89f66db162806
+oid sha256:771272a62a47d7ad9e19f47c62fad29e757a8d0a8350a23de2237df0e6f1c766
 size 149999

results.json

@@ -1 +1 @@
-{"mean_reward": 261.829138, "std_reward": 11.288109544571785, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-25T14:22:27.012416"}
+{"mean_reward": 256.7922645, "std_reward": 29.50244340698145, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-25T14:27:24.271886"}