Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 214.39 +/- 85.36
+      value: 202.47 +/- 69.53
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2b099958dec998eed58e01a598e443ddcfdbf7f4ca82564033ca1f3a5cf043
+oid sha256:47b222775b33f54423acd241f7fc7b8904afecc33dab32ff93f557a093f2aa9d
 size 146620

results.json

@@ -1 +1 @@
-{"mean_reward": 214.38632132755555, "std_reward": 85.35944944648443, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-17T18:23:18.428054"}
+{"mean_reward": 202.47247443552507, "std_reward": 69.53357534902015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-17T18:27:33.730861"}