Push Q-Learning agent to Hub

README.md

@@ -7,16 +7,17 @@ tags:
 model-index:
 - name: q-Taxi-v3
   results:
-  - metrics:
-    - type: mean_reward
-      value: 7.52 +/- 2.73
-      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 +/- 2.70
+      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:cf718e5402c54d1a9a8d810db8c930948248bf3aec23b9aa8af84afaa05348a5
-size 24589
+oid sha256:e60e717548ace789d88493aefa08177c5dc42dc0aa068d52fa4b0f8718b1ce76
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25163757d064eae2ecc5a76563be9c180d81c3f549d47fd5335706a4fde68c47
-size 109090
+oid sha256:08076417c9a7c3a7688d8a2db6155e22c527a438218edcbdbb5a3afc38e61573
+size 123330

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-05-30T17:53:56.154277"}
+{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-10-25T09:02:53.414554"}