Upload . with huggingface_hub

README.md

@@ -7,16 +7,17 @@ tags:
 model-index:
 - name: q-Taxi-v3
   results:
-  - metrics:
-    - type: mean_reward
-      value: 7.48 +/- 2.78
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: Taxi-v3
       type: Taxi-v3
+    metrics:
+    - type: mean_reward
+      value: 7.48 +/- 2.80
+      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 sha256:80814103967e7df0c3d62cd6add57dd29ae2fbb00f0751f09a418e399455a47b
-size 24589
+oid sha256:afa2ca9f3f693e10775ae828171fb6f18b781745d750a20ade4cbaf3d38bdda1
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef06c8419a314863f57b14c398b03ff73bc778463d150ee1ecd133235a7cb97
-size 105213
+oid sha256:b62435474cdf82cc5217bf9c136fa373b68346887824082f3a33afb4c125dcb8
+size 123244

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.48, "n_eval_episodes": 100, "eval_datetime": "2022-07-12T20:51:22.980112"}
+{"env_id": "Taxi-v3", "mean_reward": 7.48, "n_eval_episodes": 100, "eval_datetime": "2023-02-12T12:04:40.840234"}