Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 275.73 +/- 84.76
+      value: 290.72 +/- 25.59
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2_final.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7f7d0d2ec183e0ce36c49c5c174d1b1559dd98903b0382a3c10062ba5364c1
+oid sha256:3bdf0d7c11e23c03ad20b16c96e02bdd7d45640cfc95a731b675d57da4452a37
 size 146929

results.json

@@ -1 +1 @@
-{"mean_reward": 275.725079, "std_reward": 84.75512009572027, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T15:25:13.739704"}
+{"mean_reward": 290.7226533, "std_reward": 25.585549929996624, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-08T15:28:00.355016"}