Upload PPO LunarLander-v3 trained agent.

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 258.41 +/- 22.31
+      value: 268.64 +/- 18.79
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7945a22716d2afb758510e0315a211174e634770e6ea12f8f538db9c23ed9098
+oid sha256:3d51dfc42889d770024f90772f01c36977b1de266d8ca8ff5c53edc6ab1b4573
 size 150010

results.json

@@ -1 +1 @@
-{"mean_reward": 258.405128, "std_reward": 22.313319457700167, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-06T05:11:37.937362"}
+{"mean_reward": 268.63596, "std_reward": 18.789830820484568, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-06T05:36:33.496742"}