Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 274.69 +/- 17.03
+      value: 284.48 +/- 23.24
       name: mean_reward
       verified: false
 ---

ppo_lunar.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151c477d5d74832178e00e43cb71b8429019bc2dc4876261f95dbb615aa5cae5
+oid sha256:d5a39d3649479db771fecdde69463baab5395c763a7ffd4be6a0a4d089ddb70f
 size 147090

results.json

@@ -1 +1 @@
-{"mean_reward": 274.6871829767118, "std_reward": 17.03474111466228, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T08:38:47.224278"}
+{"mean_reward": 284.4793808843241, "std_reward": 23.237809482383383, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T08:40:55.073822"}