Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.52 +/- 2.71
+      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:a5f2a91e79afccbe65b151379677534ee9b3a605d19cce2765d6d5b614b8df56
+oid sha256:28f7da42af4631b3e3eab57788916d88e011794a1620caf3ef54a2ca7f7ac5f5
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d9dd4ec4a2026603a6a26600ae4208bb19aff68b8c79641106a3ac55a63d10
-size 97848
+oid sha256:c14e65fbc529d8b900ad83c08de955279e0cef6c6df5b2de4a4d89130aed5d3f
+size 112648

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-06-30T15:53:22.522571"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-30T15:58:25.256892"}