Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 262.64 +/- 10.87
+      value: 264.40 +/- 26.61
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7123ccd8c4c66e835a238fe49a1a7c043f57f1678d91ff46b4858d0f789f38a
+oid sha256:e3ed659745ac0c07a47605307dbfb2d82be614c2bcb8342a9f1c0822d689dcad
 size 148064

results.json

@@ -1 +1 @@
-{"mean_reward": 262.64069010000003, "std_reward": 10.873198981495076, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-25T17:05:00.738510"}
+{"mean_reward": 264.4020756672067, "std_reward": 26.605457596158086, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-25T17:06:10.050814"}