Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 242.34 +/- 74.95
+      value: 243.88 +/- 51.82
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbfa687b1e0a3858ac618255bde1cd39ffe4ddeaf9688e40729cb38da436d756
+oid sha256:d05fbfb8a6291ad16b08711b8437bac2dadfcd4723db7b327da405978a58b2f4
 size 147982

results.json

@@ -1 +1 @@
-{"mean_reward": 242.3433494, "std_reward": 74.94699031807674, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-04T07:39:33.270664"}
+{"mean_reward": 243.8813172, "std_reward": 51.821420864495394, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-04T07:40:12.798347"}