Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.56 +/- 2.71
+      value: 12.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3cb01f56bf025e6485e2232f4ed6c705933419c10b386398e5e9fb4606c205
+oid sha256:9b42b324d9fc64737a5d009c933d414ca945f4843bda2cc9ee8c8f5b75db6d70
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11dbe658e49817a0ad521491df815dfa6a23e3db9b5b421749597c2034dc8d8b
-size 101013
+oid sha256:acc5b6d25c37ef21d865edb263473e4b2ae4422b9bda6298d668dc4f512f2671
+size 132143

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-23T11:09:26.080491"}
+{"env_id": "Taxi-v3", "mean_reward": 12.0, "n_eval_episodes": 100, "eval_datetime": "2022-05-23T13:00:07.499104"}