Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 273.34 +/- 13.70
+      value: 261.62 +/- 16.67
       name: mean_reward
       verified: false
 ---

lunar-model.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7181cd7549fcff72b546230defc2cbd44337425b409a606b2595babdf68f751d
+oid sha256:3c44244c01aac73df8043e907eec39a3b589b05cc915b1a1de700ff4735f1ce1
 size 147416

results.json

@@ -1 +1 @@
-{"mean_reward": 273.3352454273238, "std_reward": 13.695261373742813, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T23:13:56.157910"}
+{"mean_reward": 261.62143517468746, "std_reward": 16.670083597761803, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T23:15:06.674117"}