Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.52 +/- 2.76
+      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 sha256:6ed1c3b8457aefb503e289e6bea13b62f3da14d12e25addc0affbb027d4802b5
-size 24589
+oid sha256:3199d699e573751755b93abd036f68042256a06ae875dd2243e32285df637086
+size 24584

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3efb1fc3001772adc6ad676f39f01ec4e2f80f908f648a44c40bed5cd6c44c
-size 106323
+oid sha256:8e6d13ae8141f08852d8305a62a1756e17c924cf519da509bbb18a8eb9aa9f31
+size 111477

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-06-22T19:08:09.610857"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-22T19:26:39.612052"}