Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 295.97 +/- 13.80
+      value: 286.58 +/- 12.84
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-newer.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72930550886613ceaa441de3b1014896c6e1ca7607943f1e5444144160464ef
+oid sha256:eaab1669d702d6daa9f0f280c7f2b9191fc90e5553cffbf540e775791b58604c
 size 147929

results.json

@@ -1 +1 @@
-{"mean_reward": 295.9680892933675, "std_reward": 13.801095026214778, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-24T13:27:49.246834"}
+{"mean_reward": 286.5770914470061, "std_reward": 12.838566395136697, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-24T13:29:37.180787"}