Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 234.67 +/- 45.06
+      value: 248.00 +/- 19.09
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7436cede7737daa594c0602cb55e5dcf565f44528f9476965a6b4454828c4e
+oid sha256:3deda3b78d65dc649154136b9c80088093a1006a978f3c97e5d646bc30cb782d
 size 149559

results.json

@@ -1 +1 @@
-{"mean_reward": 234.6715921398135, "std_reward": 45.05758053324836, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-30T10:41:45.358933"}
+{"mean_reward": 248.00468527959055, "std_reward": 19.089447868342123, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-30T10:43:13.863755"}