Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 280.90 +/- 20.68
+      value: 271.08 +/- 19.45
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3-test.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4fdccb76b2bd7dfe22a476b240d722e37f0e68fd337defc01b7420e6265f3af
+oid sha256:e54d70a70f62d21fbaf23e69555ebd9a9383747003ca9469f65d742e3ea08644
 size 151159

results.json

@@ -1 +1 @@
-{"mean_reward": 280.9045056257995, "std_reward": 20.67891221213955, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-05T14:40:04.476059"}
+{"mean_reward": 271.0845659144873, "std_reward": 19.45395584946216, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-05T14:44:53.945404"}