Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.54 +/- 2.74
+      value: 7.56 +/- 2.71
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfde344dff8d667f275ccf91fd2cf8ba81325b9bc50a7fd7d97331442a7dee3b
+oid sha256:b76fb2d00b1794dc76443dc16dd9a48db3a868eea0f5a470ebfe6a50a353463f
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326e75db9f534609e4fa7c4222cc6cd7f1a2e77ddd54e1e96467025014cf7618
-size 110937
+oid sha256:41dfaa0fd78ca8a89a35bef56bf3102fa0a57fc5328a4662effda7309006ee77
+size 104769

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-07-07T05:39:59.358121"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-07-07T05:45:10.881843"}