PPO LunarLander-v2 trained agent

PPO_75.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e268b9d53559fcfb0b111799b4b714cf031a991d865c3aaa1b5f0a81b82cf4f5
+oid sha256:ddf534c85ded9493c3a751b19b79cecadfdf4204fafd53166c3107a73b80f56f
 size 150461

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 285.94 +/- 14.09
+      value: 284.45 +/- 12.78
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 285.94482419999997, "std_reward": 14.090797257207049, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:06:04.065921"}
+{"mean_reward": 284.4504327, "std_reward": 12.775214591664712, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:06:19.551953"}