Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.52 +/- 2.77
+      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 sha256:859fa8c2487e080492dfc05885392bb21aae777dc21d2cd634ebf330948cca21
+oid sha256:ce3cb01f56bf025e6485e2232f4ed6c705933419c10b386398e5e9fb4606c205
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e27c194c3df5256c10bb535fb4c20bef0b516cfeb52c7489adc06668fd4f1d
-size 109062
+oid sha256:cf41dfd81b2a16df5d5cf4a21f7e3cd78005399e4153344f561b94c51c3c97f1
+size 106632

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-06-26T09:40:04.194097"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-26T10:10:48.245002"}