Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 254.84 +/- 19.63
+      value: 250.91 +/- 22.87
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82581614b28754f1b40407d8191deac4d32c17b905012bc49b230b7a82d2ad9a
+oid sha256:cecf8f3ac4481f389b5a286cf3c5e250052caee64ff465aaafcc866f62741391
 size 151280

results.json

@@ -1 +1 @@
-{"mean_reward": 254.84324529999998, "std_reward": 19.63058305989858, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-09T16:44:49.411183"}
+{"mean_reward": 250.90713590000001, "std_reward": 22.870538646891763, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-09T16:52:54.590324"}