Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.54 +/- 2.71
+      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 sha256:3e9f94916fe491cf97ef2fb97742e1febf1573090ebd3acd6d826fa5a6449371
+oid sha256:158dc3401a83fd36e24102731cbcad2716584c9a52c419f874f8d10572d74d0a
 size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5296fc9b7113fc076777bdf91ea4bf9cecbaf97511672e2cef63ac2992e6b781
-size 109106
+oid sha256:c0a29238eca4374a8866bda18c60d619a0853cb114db309ef51324153e149dbe
+size 108879

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-05-23T22:33:02.653857"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-23T22:39:38.732429"}