Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 7.24 +/- 2.59
+      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 sha256:0ac9192453fec393ec822a6200fcae7fa8f95370e19eb0b0973745992c6cf8b4
-size 24570
+oid sha256:806d1187d419246b4d1ae6a84d9446c31ed138e063651cb4f77692e165f4d3c9
+size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9d166dc53037d285554f62b5f134495b6963d320aa6ecce86cfe4d7b79df20
-size 112091
+oid sha256:a4eaaa363b1ce9a1af7f2dd3d19fa6f90175fb145d1d6218c0d894ede5ff04f2
+size 103590

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.24, "n_eval_episodes": 100, "eval_datetime": "2022-09-14T21:16:43.520807"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-09-14T21:20:42.656529"}