Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.50 +/- 2.75
+      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 sha256:791cccf0fdb7a4f9183967b25aae2bb825adf5ac398b2e793ff2b8023c7cabff
-size 24589
+oid sha256:e5ba42918e2428e579ef4c22d4c93272d80b9ae10c0a404e37c397fb824003c4
+size 24592

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a95f7745c2b6139be01166b6e54d3343f7796fc219ce30569345836562bd03
-size 117147
+oid sha256:e24b5a30eae34fa0f84eee83f89470b309ac25485e681ddae5533acf330bdf82
+size 126557

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.5, "n_eval_episodes": 100, "eval_datetime": "2022-08-12T03:28:21.710254"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-08-12T15:16:56.129460"}