Run2-271

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 271.31 +/- 18.36
+      value: 258.66 +/- 40.04
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebdcdee26b73e0c5cdba478998addf2d19b5b87d5a4ef1df33171953768d342
+oid sha256:01d3df409787827969dc55a2c68742b61aa0493ff48d68a2761ed70efc2e5e01
 size 148041

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfe9d1e148854eda9cd5811600f7bdc59c031584a76f689d2ffb91c73d8f9ef
-size 124578
+oid sha256:3d688dc93444faa34fbf456e0349b90be080dc7cf7f74b68fb1340d2a9448ca0
+size 127072

results.json

@@ -1 +1 @@
-{"mean_reward": 271.308085, "std_reward": 18.357892429701838, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-18T00:31:50.731080"}
+{"mean_reward": 258.66204329999994, "std_reward": 40.042819334480804, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-18T00:32:26.538209"}