Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 241.58 +/- 20.78
+      value: 232.77 +/- 23.14
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0e4bb1e871c403256aa54f89a9c07a0e743fdf35d5f647bd6545953fa63c5e
+oid sha256:799c71fdf5dd3e99b6666fcba274ed1abe92254e96856fe6ebabbe4f5f24ca15
 size 150710

results.json

@@ -1 +1 @@
-{"mean_reward": 241.58005784104725, "std_reward": 20.77953269362652, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-08T18:34:19.030770"}
+{"mean_reward": 232.767027, "std_reward": 23.144133774007834, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-08T18:37:20.597798"}