Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 251.64 +/- 15.12
+      value: 261.11 +/- 23.87
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aecd923d9b160b0e5237946c011eba97d97ddfb84717fa570202d9da02d358b
+oid sha256:20b629165b8a330e8dbb71cb58e48025d69d4fb1bba0b65f5b0b71fb6e934376
 size 148064

results.json

@@ -1 +1 @@
-{"mean_reward": 251.64060828430146, "std_reward": 15.11755997770337, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-30T23:16:41.883427"}
+{"mean_reward": 261.10864127345815, "std_reward": 23.870578653826755, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-30T23:17:06.147682"}