Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 281.16 +/- 20.86
+      value: 284.04 +/- 21.82
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c999a0f7f5578c1cdc8b29625c49cf99c84a91fc188847c656f63d1141d606
+oid sha256:188e0ab0e2e3fc58b150d8603b203c8ccab7708a1687f195caeb6d4120533fac
 size 3264877

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d848fc6d6edc1dc8b207c8e3410b4eb16234cc7939b4e02a8ec63cae4bd9b1
-size 148052
+oid sha256:fb45c04866c39a714211ee07bfba86cbde7c7ff26288ffd00bd50aac92f29894
+size 149203

results.json

@@ -1 +1 @@
-{"mean_reward": 281.1604439851664, "std_reward": 20.85592198001221, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-08T14:17:06.861833"}
+{"mean_reward": 284.04043979403815, "std_reward": 21.816007688633288, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-08T14:17:28.763681"}