Upload folder using huggingface_hub

README.md

@@ -7,16 +7,17 @@ tags:
 model-index:
 - name: q-Taxi-v3
   results:
-  - metrics:
-    - type: mean_reward
-      value: 7.56 +/- 2.71
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: Taxi-v3
       type: Taxi-v3
+    metrics:
+    - type: mean_reward
+      value: 7.52 +/- 2.73
+      name: mean_reward
+      verified: false
 ---
 
   # **Q-Learning** Agent playing **Taxi-v3**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3cb01f56bf025e6485e2232f4ed6c705933419c10b386398e5e9fb4606c205
-size 24589
+oid sha256:85eac953f200726ac8cc872362b43829ebd8a2c4ba779072b0156ee028f10504
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff92c0178b052a4d1ab781693c791eb9a509cf3b65f3b1bacc644ea9f4ffc075
-size 106900
+oid sha256:7c2aea5349826fca01c94c3d95b269beff72f242979f93f60de8648a750bccaf
+size 116887

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-27T13:27:24.982180"}
+{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2025-10-09T09:40:44.042266"}