Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 7.54 +/- 2.71
+      value: 7.56 +/- 2.71
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5954d86c04f63c0d5b5fcd28b7fbcdd4903b690985e0d9be36b73e42531c4c45
-size 24570
+oid sha256:4afdee84b6492cef1c034a7dc18ebf7b472bffc69bfc675ed88e639057ad100b
+size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d48f592b6014b0c6d7d3e008948ca617051653fbe2e5909fbdfee89681c5c5d
-size 118611
+oid sha256:3c1c1502972b369a3e10fb1e22d10ef26b2aaff90c6fb2656f64a09309062c4c
+size 100065

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2023-01-27T19:36:32.301371"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2023-01-27T19:46:21.893156"}