Trained with 1million timestamp

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 278.84 +/- 18.14
+      value: 276.57 +/- 9.48
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb0a35fa315ed15adbd6103d801cdde74ee213dd2d253afc98f3f27b66f9b1e
+oid sha256:1dc5f178f50c1c117a935a0626d14eb8a66faaf0db2c39e9a78e5b368dad1dfd
 size 147897

results.json

@@ -1 +1 @@
-{"mean_reward": 278.83734990000005, "std_reward": 18.14397085349778, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-09T22:04:38.564139"}
+{"mean_reward": 276.5717152, "std_reward": 9.47997678293303, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-09T22:51:26.118728"}