Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 269.89 +/- 13.30
+      value: 273.34 +/- 13.70
       name: mean_reward
       verified: false
 ---

lunar-model.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a014dad6f7319b906d50f5e09891723cc4155d27f331b5303a9a51017f6df383
+oid sha256:7181cd7549fcff72b546230defc2cbd44337425b409a606b2595babdf68f751d
 size 147416

results.json

@@ -1 +1 @@
-{"mean_reward": 269.893570140434, "std_reward": 13.299542646344, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T23:12:10.226822"}
+{"mean_reward": 273.3352454273238, "std_reward": 13.695261373742813, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-10T23:13:56.157910"}