Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 273.06 +/- 20.60
+      value: 259.67 +/- 13.09
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f96b4727c8aec4dae8c44e5ee57392ffd25686a1d09b952fbb8bd0cd4352e33
+oid sha256:ad700a6e0d8b86a81981819eb9b65aed2d87501bffb2c542e46b5acf0b952c6e
 size 150002

results.json

@@ -1 +1 @@
-{"mean_reward": 273.05532159601256, "std_reward": 20.6000727603246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-19T18:59:27.038530"}
+{"mean_reward": 259.6669151, "std_reward": 13.094986940149909, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-19T19:10:46.186616"}