Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -7.87 +/- 14.62
+      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 sha256:70a9799de78b305196feb3e01761631824e272876ee85ef724b473d7351d5bc5
+oid sha256:5e84042d6de1c1a5ad4c051c09753fdebbec9de786eb06399987190771d63d81
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cddeb2b6458350256bca0a4237d02090d182ce7da98bd1a872479a91ff6ad3e
-size 106225
+oid sha256:c8195c5e43a3018545942612f307819aafe1ed394dae1397dba108eac2e37d92
+size 87043

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": -7.87, "n_eval_episodes": 100, "eval_datetime": "2022-05-30T20:54:53.139000"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-30T21:00:57.716503"}