Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 248.59 +/- 22.40
+      value: 257.75 +/- 18.22
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb5057724d9544ef4858889a4c5cde5ad98d80f01c9253bc50e4b1a0e29f7f3
+oid sha256:d83ddffd1af7f2888955df1d0d305bd56b89fb3ae48780dc6a0685b203807384
 size 146741

results.json

@@ -1 +1 @@
-{"mean_reward": 248.59347020000004, "std_reward": 22.3959706776593, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-25T18:19:24.600780"}
+{"mean_reward": 257.7499332, "std_reward": 18.218990240316984, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-25T18:24:40.446497"}