Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 7.14 +/- 2.64
+      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 sha256:77627341abe7e67f5f85545716131cf5e4a944a79e3e41812e988500947e5ab6
+oid sha256:ad2ced43fd14a1edb7219dde1f5d2258f68c43dbf1e7ccaa8649e93adde6bb5b
 size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd2dd9dafacb7926239bcb4f568cb63f81cba11c0a1cfde4cff0a49d064cee9
-size 116923
+oid sha256:252d8e63e6979f9d062719465efcca1c350425e5e6d003fa24c2eb611ad47d3e
+size 117044

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.14, "n_eval_episodes": 100, "eval_datetime": "2022-10-16T19:43:07.856026"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-10-16T19:49:27.365524"}