Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 282.71 +/- 19.58
+      value: 295.71 +/- 16.23
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-3M.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c964f2e832b0912f41da9f8d4bdf66812c9f511c28762df0939da758353ebdcb
+oid sha256:7077e54c75c2370906de4e2f52d697987dc276f6eefc4bc638978d56165272fb
 size 148171

results.json

@@ -1 +1 @@
-{"mean_reward": 282.71094042575197, "std_reward": 19.584607895674083, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T03:00:07.053983"}
+{"mean_reward": 295.7121618696202, "std_reward": 16.234141119651046, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T03:00:29.927178"}