Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 264.75 +/- 25.34
+      value: 257.87 +/- 16.53
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c22827d70b799f083fc03595b07add7f6e5e26c81de1384ce6141e8414bf37
+oid sha256:fa59c7401f27ce3f1dcb0c6abcb0634603ae270e0e01cbd152fb38fc18ce9f05
 size 148064

results.json

@@ -1 +1 @@
-{"mean_reward": 264.7472092, "std_reward": 25.343491284683505, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T23:04:46.524213"}
+{"mean_reward": 257.8698811986936, "std_reward": 16.534997237842145, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-12T23:05:39.523621"}