Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.56 +/- 2.71
+      value: -10.17 +/- 40.27
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3cb01f56bf025e6485e2232f4ed6c705933419c10b386398e5e9fb4606c205
-size 24589
+oid sha256:7abdf6b5aff8c1891e4741024d8a3745394e92649bf84d549c8eacc2ee760bf4
+size 24620

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:677bac8abfcde390641d6adb928c1daba6e23aa04491a1364c6dd9857533b28b
-size 108707
+oid sha256:92afe94b14ce62e22bda2655f07aac96e14f64977592e2eda2ae28503ee7bdae
+size 97696

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-24T13:23:14.366601"}
+{"env_id": "Taxi-v3", "mean_reward": -10.17, "n_eval_episodes": 100, "eval_datetime": "2022-05-24T13:38:05.831066"}