Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.35 +/- 0.48
+      value: 0.46 +/- 0.50
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88736e9003fa5b2c6f90a5341087c98d2d084f75068f392fb1e7b01fa7ffe1e
+oid sha256:76fc7d0218109bee009e1edcec2dc0c6ab7d839e183640594a465be4abdcc104
 size 2458

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8677c318ee9d002df0d64e49077bb5619fcf62f0d43e9b60ab31c79f3643a394
-size 169423
+oid sha256:b0f5c4f6d506f0a11b1ad77dcf238eaed292914a122b684ba43c55a3cf6546ef
+size 168422

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.349, "n_eval_episodes": 1000, "eval_datetime": "2022-06-06T16:06:10.659835"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.462, "n_eval_episodes": 1000, "eval_datetime": "2022-06-06T16:30:56.776194"}