Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.54 +/- 2.73
+      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 sha256:94fa0351198b5a1dafbd4a1a1fb82c901e2c583478245131255414ac6d103390
-size 24589
+oid sha256:65b80f0cf2d3194385177bd9f2dcbb3f9d3072065392c541262ba76c044ed8df
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1a7569b61ae8fca46afd92f13370d0c2fd8be4074ec7cde58b311d2e9238c9
-size 128667
+oid sha256:644d40e0911b5aaca1da5a67154701793e211cb8ef83c6ae0cee2c8643db8b8b
+size 125538

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.54, "n_eval_episodes": 100, "eval_datetime": "2022-08-08T14:35:40.868903"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-08-08T15:01:59.502797"}