Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.50 +/- 2.72
+      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 sha256:9761e4e3cfe7bac87edb3af3e06bc1fcd72c7c597fe4acfabb4da8106b1549cf
-size 24589
+oid sha256:66f4edadfde63a35db046eb4461e66c28e3ee24d047cf81563dbbed4e3abeaf2
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b84244c18afaf49d9b1428cd54192d564fd1100062d60a6911cba31898b5916
-size 107012
+oid sha256:777d5e1295f2c6e649c37c8bbe89081d27786ce1bd1c02d1e122af5db784cb23
+size 101102

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.5, "n_eval_episodes": 100, "eval_datetime": "2022-06-04T18:53:54.774744"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-04T19:15:04.929851"}