PPO LunarLander-v2 trained agent

PPO_90.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d032ddff529a1384b6582e855013af52876a79f05be73e976c22d6763a83d44
+oid sha256:78aa8c995ee2136d9be9bee720b0ff20b321c8f4c5fa34d76bd6a6e7a15c0396
 size 153027

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 290.26 +/- 19.07
+      value: 278.67 +/- 14.53
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 290.26426640000005, "std_reward": 19.074336292581158, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:08:59.305358"}
+{"mean_reward": 278.67126140000005, "std_reward": 14.534810999481111, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:09:15.592953"}