Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -136.75 +/- 27.11
+      value: -129.55 +/- 22.91
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8608586c4ecdab7e3fa48e8118a4baeba7accedb86d966f3f9e6903841e763d6
+oid sha256:8f9a4ec43291c047e69400cf0c0c6ea20f5f5ce7003c1d8549ea5f21666626e3
 size 147947

results.json

@@ -1 +1 @@
-{"mean_reward": -136.7489822, "std_reward": 27.108563780616358, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T05:49:46.902834"}
+{"mean_reward": -129.54809327020774, "std_reward": 22.90922609052324, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T05:50:24.955627"}