Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.21 +/- 0.41
+      value: 0.02 +/- 0.14
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c52b838f0bf5cd7ae22037882507d99a3ebbf5617b3f6f5c4c0c2a70a6955f3
-size 2457
+oid sha256:9140b66450d9f43ed691235bd6b052b57d3bb28ff4bd974c31b98691a90eff2c
+size 2459

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc02b3b57b1af2e064108e4a5dbac17b37fe15575e18d39e8c21373ecce4bd1c
-size 131330
+oid sha256:f5de50c87ef3c30d47f544c05a009b2b36c8b6100ca4af01b3a0d2fca7ec272d
+size 136298

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.21428571428571427, "n_eval_episodes": 100, "eval_datetime": "2022-05-24T12:08:28.140253"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.020833333333333332, "n_eval_episodes": 100, "eval_datetime": "2022-05-24T12:35:01.332686"}