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: 7.54 +/- 2.71
+      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 sha256:7e02d469ce530dbf896dde80c46fdd8affb07778dd7a649c5077a73bf013e2a6
-size 24589
+oid sha256:42c9a7ffae73655cb4e4888b90368a38d7dc6a22df133b617120583ec0d6c8a4
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5af930481df073de730be81c80471a1d1b50b878e65e51a7480dc3fd6fecb1
-size 106898
+oid sha256:055ecfac9d80a17074d68bcdcf9b31ab983066b7dcb5fcdc74d7a6640d3c007b
+size 125790

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-09T18:48:42.053049"}
+{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2024-03-09T09:38:00.251741"}