Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 246.74 +/- 63.87
+      value: 270.59 +/- 17.06
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f246c2783f00de02f9facd5401538b2916543db4786dc7291c51190890662a
+oid sha256:57cc1e39936c6f65a0826712b590e4fb5c20803cbb3eb47d215d1756bb62205c
 size 148028

results.json

@@ -1 +1 @@
-{"mean_reward": 246.73923419999997, "std_reward": 63.868005048528474, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T06:30:13.239539"}
+{"mean_reward": 270.5892668, "std_reward": 17.055185244638185, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T06:32:40.877745"}