Improved lunar lander more timesteps 2M

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 275.47 +/- 20.40
+      value: 286.04 +/- 21.70
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391164880e6908eb630999796cd0ed8f861e9eb849dcad0cdcdb908936156bea
+oid sha256:c44a45a5053a6aebc1ecde54e8bf4400c9a3ca33673b75e187aa0058eb9941e4
 size 147921

results.json

@@ -1 +1 @@
-{"mean_reward": 275.46841639999997, "std_reward": 20.40064401260657, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-19T08:56:17.863927"}
+{"mean_reward": 286.0435971, "std_reward": 21.698875790642056, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-19T08:56:55.610725"}