Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 284.98 +/- 19.77
+      value: 286.04 +/- 19.40
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0027adb04fd9596ed3fca006f0a7ef5bd67c5d8812df3de1804f67a4ae7a3249
+oid sha256:5b049dd0b7c157650addc668fcd926d0135f955767eb9df6b39bb396a212749c
 size 147279

results.json

@@ -1 +1 @@
-{"mean_reward": 284.9821084709732, "std_reward": 19.77087335963914, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T01:21:09.590422"}
+{"mean_reward": 286.0392296147072, "std_reward": 19.39845305652458, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T01:21:49.246372"}