Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 7.50 +/- 2.75
+      value: 7.50 +/- 2.76
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fdcb6bf67d745bc97f06c5eb357ebeb9dc024c718c665ba53cfc2e437071cf
+oid sha256:e0040f9aa7115c94d3056546cc78be9d96bbb5a70f473424267154f31f74c8a3
 size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee088f303069a17a63148452bc761bba068520edeb30bd4a2be4edc5ff9fe5b
-size 110589
+oid sha256:a1f7b6f1ada9408d766ccad15129467fe921ddb88d0d009370d1ba5598a3bdee
+size 129523

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.5, "n_eval_episodes": 100, "eval_datetime": "2023-02-03T09:16:11.626187"}
+{"env_id": "Taxi-v3", "mean_reward": 7.5, "n_eval_episodes": 100, "eval_datetime": "2023-02-03T09:17:24.188205"}