Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -45.13 +/- 49.16
+      value: 201.93 +/- 71.79
       name: mean_reward
       verified: false
 ---

logs/events.out.tfevents.1751133766.Office.37855.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c5909b1951b2b33fd7ee4c92965bea4c8f2747c03eb30f656a7e5e72b08e8d
+size 898029

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5e106fbc376997ccc4d65f699e3486cff3ca1fff3ea1e44e6742a5600d52a3
+oid sha256:ecc5d04a1ab8ac44671ce0e12a48f9d5b4ae14995b8335eaa5e0d867d6837b03
 size 43026

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8e978f21676e815563618a8014ab0b1752c7afb2b83544968819e58b13df39
-size 223218
+oid sha256:7b76300bfb722d60675f311f20289f23b925aab54178106cf45c06d1c9ced0ab
+size 101011

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -45.13177436320116, "std_reward": 49.15505376863384, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-28T19:03:02.596726"}
+{"env_id": "LunarLander-v2", "mean_reward": 201.92693937451003, "std_reward": 71.78926813765575, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-28T20:16:18.926136"}