Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.52 +/- 2.67
+      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:adc90a3cdc9ab187fedaa2d09184de35a09a4348349f6d25f9465eb3fe4f8488
-size 24589
+oid sha256:76824c9596e3597f72c4832fd30370db3eac5ba174dc41ea28894346b309ad8a
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:043c21a9c57c27900aeeae196299eef800ab2984703cc599b8fd1ddf0d806741
-size 100834
+oid sha256:1aaa398c20738c1bd737c7a127feade8e6916b8228c59dd0de8e4dc78285a653
+size 105915

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-06-17T20:20:30.388464"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-17T21:04:16.205567"}