trained the lunar lander biyatch

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 263.38 +/- 21.40
+      value: 269.93 +/- 19.32
       name: mean_reward
       verified: false
 ---

ppo-lunarlander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787170b833a42638d01a2bb4ff7823ae1cbc9da65dd2da3487179c07816d3caa
+oid sha256:e72dfdabee0f88905e18deaafdc0db78d3089b1efb1883cc3e69ae8be772097c
 size 150258

results.json

@@ -1 +1 @@
-{"mean_reward": 263.3849263, "std_reward": 21.396144838462153, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-26T20:08:30.607989"}
+{"mean_reward": 269.9263682634268, "std_reward": 19.31669326846697, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-26T20:09:31.962259"}