Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 7.46 +/- 2.81
+      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 sha256:0cbc65a51f1dd2dbea85150707ce8ae9dd8d98ddcf94b704ef7706523fa86203
-size 24570
+oid sha256:4f6df75379760a93b5ec0213a211af14efe8e609c27f9dc4a9136dfa02357880
+size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d36f088cc7f2c0dcb995e99215f58e83cd6b6c03f2c9327082dd36c4df9841d
-size 113870
+oid sha256:73497e669988ef5a28e73793b828c90ebaa7d436353f60bc7e660c8df37c0f10
+size 123026

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.46, "n_eval_episodes": 100, "eval_datetime": "2023-02-15T15:33:13.303359"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2023-02-15T15:38:40.550656"}