Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 265.41 +/- 20.11
+      value: 267.60 +/- 20.35
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf46b35bdd3599cce4aa1b413594d31fc9e9ed326ce7334f70e2ef7548415a4
+oid sha256:12637892acf4f3857ccae8ba0634904ae34e6fe0de9ddf557b3788e7a1a6fb37
 size 150084

results.json

@@ -1 +1 @@
-{"mean_reward": 265.4115308, "std_reward": 20.10908933568378, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T12:54:05.323745"}
+{"mean_reward": 267.6023644185344, "std_reward": 20.352182582420735, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-20T12:54:21.017522"}