PPO LunarLander-v2 trained agent

PPO_90.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78aa8c995ee2136d9be9bee720b0ff20b321c8f4c5fa34d76bd6a6e7a15c0396
+oid sha256:60617a2464331b02fad36e6e1d2a674b55b07ee90a67b9ab4a00c0ac36918c58
 size 153027

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 278.67 +/- 14.53
+      value: 275.22 +/- 18.90
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 278.67126140000005, "std_reward": 14.534810999481111, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:09:15.592953"}
+{"mean_reward": 275.2249163, "std_reward": 18.90070324267402, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:09:31.429511"}