Upload . with 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: 7.46 +/- 2.79
+      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 sha256:7388c6f3ba1f97c6d86cf1f9327e6f9294193af305b69f425bf63177dd0b1159
-size 24589
+oid sha256:a1d93726092f535e9cdecae94558c04565cb833dd18a078f50c12a33a68a1379
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8d02dd76aef8d5cf010f2f8bf0d2240b3ec00c5fe7c547f9bf5b97a40e871b
-size 112336
+oid sha256:14d66b621bca3d91e72360e8512270819e2a3d9da538083fd310b948319793c7
+size 120355

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-28T05:49:29.662441"}
+{"env_id": "Taxi-v3", "mean_reward": 7.46, "n_eval_episodes": 100, "eval_datetime": "2022-12-26T08:53:57.785811"}