Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.42 +/- 2.85
+      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 sha256:49cb23340991863ef8d1b20242a5212ca8a97540667952121357643b8b7a5a97
-size 24589
+oid sha256:ab8e95128e6ad98b6edb4f3ef13cfa0c3b02c715472e7b25929f6efc8cbefa16
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68db4c161ab15e11ca135ec81f00034b5609f0429015fa844a1861807aed3c66
-size 110886
+oid sha256:511f1badf6bf6060eba35b70303c0d78399392862a0e5edb0dfadf074a380432
+size 103004

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.42, "n_eval_episodes": 100, "eval_datetime": "2022-06-07T01:01:16.930293"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-07T01:19:47.302155"}