Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.54 +/- 2.69
+      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:d09186798add55dd889aaed79c68cdd88d0076bc64d130e5f09fc9996aad3aac
-size 24589
+oid sha256:0c9e660132c4fd84d2e6c44b8e2cdeb692f6744899b0e4f341b4ee6665fcd291
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8221ec1591c728377d6503c420d566be7f8892bcc6f095a0e7ef8c41174b5ba
-size 107333
+oid sha256:ec0a6f2ce199a6e83bb98d40dcd7f0cb50bebb461502443009042909c53956e5
+size 101092

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-07-02T10:28:18.014310"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-07-02T11:26:33.108600"}