Upload PPO LunarLander 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: 272.38 +/- 21.29
+      value: 264.76 +/- 46.89
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3ebb71cb168c0085b231cedae14d13df3f0c9c75b8f55d4091d8dc3f735ce4
+oid sha256:d48534f090378255ec6d6e9cc29ae9dd18546f8889aa3cc8ddb48f272eddea28
 size 150567

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26ced20206999eac81adca220abdb316442bbfdda4d7196bcbf5f217841505e
+size 167802

results.json

@@ -1 +1 @@
-{"mean_reward": 272.38202739999997, "std_reward": 21.286035833205357, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-23T16:11:40.564855"}
+{"mean_reward": 264.7566769, "std_reward": 46.89151948494028, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-23T16:22:32.452710"}