第二次上传

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 266.13 +/- 15.33
+      value: 255.18 +/- 24.14
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902a748e30841d6d53b1e8a7d268f69f8834a9330dd9ac1e317129af85347fc8
+oid sha256:50689717cb241f3ecb7a9c58752f21c2dac87e4179d2076e3319a4c5c804ea00
 size 150006

results.json

@@ -1 +1 @@
-{"mean_reward": 266.12500082802086, "std_reward": 15.326626450894773, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T10:05:41.872030"}
+{"mean_reward": 255.1841824, "std_reward": 24.136411790516096, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T10:27:42.000564"}