Re-upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 243.30 +/- 63.34
+      value: 244.54 +/- 34.70
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79135a3f2b77a79800bcb8ac286ca1c5496ace2142d12c4f32ae9566384f98c
+oid sha256:d551bd346bc281941720c382d2589b00e548649fd5590f1ca342abab46ac676b
 size 146927

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f73fbda263effa8fb0b480f0d7ae20c4814a013353853f672742bcec46385b
-size 168152
+oid sha256:48507006e2e926fd5bf294843d24d8a54aded85acf64351f9e8efe7bf795892d
+size 169602

results.json

@@ -1 +1 @@
-{"mean_reward": 243.30090729999998, "std_reward": 63.33605713718836, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-01T15:10:35.638570"}
+{"mean_reward": 244.5359113, "std_reward": 34.70343034990781, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-01T15:18:48.365640"}