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: 273.50 +/- 23.66
+      value: 283.32 +/- 20.20
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f0f3a53d071d289081c6812204c180e55cc0b86a28d86660ed5ab05a3100fa
+oid sha256:8587531fbf19078d955e4fc6d564386277a96ce3db8619346a6830895ddf7973
 size 150007

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56be34fc304f4e47d3b008f84f9c6d4710b3e1b01986aa7c1241ff6343763736
+size 159624

results.json

@@ -1 +1 @@
-{"mean_reward": 273.5013919, "std_reward": 23.661730271330974, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-13T11:38:06.657207"}
+{"mean_reward": 283.3232994, "std_reward": 20.20340408892127, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-13T11:52:27.953670"}