Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 256.46 +/- 82.79
+      value: 286.17 +/- 19.26
       name: mean_reward
       verified: false
 ---

models/unit1/ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad99587dcc4e41ab78bcf1e6d5f79762776331caf9cfaf6127cb520e871e8318
+oid sha256:b199717158e8caca02601eeb1d2ec9fe0128a014ace65080f9df5cdd3baa1b68
 size 146621

results.json

@@ -1 +1 @@
-{"mean_reward": 256.46099550618294, "std_reward": 82.79155995118684, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T15:07:55.678681"}
+{"mean_reward": 286.1741539206721, "std_reward": 19.264489630511093, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T15:11:23.216135"}