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 sha256:0fdc5482d946181319d367ee055cc766d1da14b99bc91e9660bffaaeaae2ac2b
-size 24570
+oid sha256:e726e66238f5a03323cad28aaeec12b451531bc3d2c9968f3c3391b01a43b670
+size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2867651ccd8df38a31d4d18ff4dc11120946632739bde8dc30a6b9bde283e807
-size 119172
+oid sha256:158226139ffd6765234fa3ccbd01f8ec00d913bfb780f347a42d242a4fd05a5d
+size 126478

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-10-23T17:48:10.767684"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-10-23T17:58:00.085658"}