Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.46 +/- 2.79
+      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 sha256:89c84ba60ee0307f2ea9321539ab5baa01bd35c63c50a6bae5da49022af2d44b
+oid sha256:f2e3830ee8366135da629ae20bf77741ed770e8710787a7b49ab2f19b03bafe2
 size 24610

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbddda939461698b3c8c6ee7594cd406fd66abad4f835f7f8c168c840d5e740a
-size 103046
+oid sha256:15872a77f98d341b378c7cda6ef96b4e6cfd79fac541359f88b1c98f0d8eb724
+size 108893

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.46, "n_eval_episodes": 100, "eval_datetime": "2022-06-29T14:08:06.277500"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-29T14:14:52.155472"}