Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -133.71 +/- 37.58
+      value: -140.00 +/- 84.02
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf41ab599fb202206943586d06fa3e4179c4ebd043e37de71cfc465b4db53d19
+oid sha256:c371cb0862cfb81eeaa33f1b85da64f5a9eb7276b58dc746a9785fd63c693220
 size 147017

results.json

@@ -1 +1 @@
-{"mean_reward": -133.70931102819813, "std_reward": 37.5787005567661, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T23:53:04.291603"}
+{"mean_reward": -139.99547893845593, "std_reward": 84.01914934580873, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T23:53:36.064053"}