Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.52 +/- 2.72
+      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:d30901e6aabfddbc83fef44b6b91da7b4e6d2e2199291b8e9d196e8dcde9d102
-size 24589
+oid sha256:fc3ed3cbf0eb5186c9a3e8161cea778fa9ead9bc84fbb06e981053ce7a35a585
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca34ea4eea92d7b2b2142e4d49910e816ca4e4674ef0ffa1428b735d37117a0d
-size 108732
+oid sha256:09762c63e1b912cc0335f93285cb968c65a4e075abdfa7d08e4c7c02e6bda61f
+size 105199

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-06-07T05:36:45.327320"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-07T05:47:11.535157"}