Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: FrozenLake-v1-8x8
     metrics:
     - type: mean_reward
-      value: 0.59 +/- 0.49
+      value: 0.87 +/- 0.34
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dfa5156050bc4f663a761ac1c68a62f64c151b863ad1723a7702ea895ef6f09
-size 2439
+oid sha256:a7d5c9827a4973755258551f8b1f9495f2557e664af1c1d7756b14064aec75ca
+size 2438

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf58bb0e3da94f82e32f667500f55b952da427910bfdf65ef87aa0dc7804f4dd
-size 152773
+oid sha256:165e7fb0fb0ef48c523a91f4529a43eaa4f6252ad98eee2adee452b0f49e510a
+size 175822

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.586, "n_eval_episodes": 1000, "eval_datetime": "2022-09-06T05:02:00.720254"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.87, "n_eval_episodes": 100, "eval_datetime": "2022-09-06T05:03:51.204060"}