第三次上传

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 255.18 +/- 24.14
+      value: 272.04 +/- 13.76
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50689717cb241f3ecb7a9c58752f21c2dac87e4179d2076e3319a4c5c804ea00
+oid sha256:4a1cb1027220158a2149fed7606165b6eb05fc0875987c63d31d1a9d66d0be17
 size 150006

results.json

@@ -1 +1 @@
-{"mean_reward": 255.1841824, "std_reward": 24.136411790516096, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T10:27:42.000564"}
+{"mean_reward": 272.0399663446734, "std_reward": 13.758080047853994, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T10:38:22.839796"}