Upload PPO LunarLander-v3 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 177.85 +/- 62.03
+      value: 147.28 +/- 91.01
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3-baseline.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214f26379bcebf5ca64b8e1beda01488586dfdd9a3d70bc83bb3f89bb80af693
+oid sha256:51a4557861d19a0c6dd332c1adb7f51fc7423893ee483674d17b4d29215bd241
 size 149305

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdce6f7c1b66e26bd45778a4bf81dea476618958c0db1fbc49198b5d3ba614ea
+size 175816

results.json

@@ -1 +1 @@
-{"mean_reward": 177.854861, "std_reward": 62.02989829519539, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-24T17:13:51.050970"}
+{"mean_reward": 147.2826913, "std_reward": 91.00756265514487, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-24T17:19:42.723230"}