Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.14 +/- 0.35
+      value: 0.78 +/- 0.41
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f708a05696bf2de7216c56954fc471baa8ebb62499c01ca7e6b809d25be3b0e2
-size 921
+oid sha256:7b2ee9085afba4c794e91a3b90c05ff51a314424217783f44ce7f7bcf32d2d52
+size 914

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f40f7fc67ccb01e5b648b275546c0198f234b7332dcf34c44e9b3612a9bcf49
-size 24958
+oid sha256:822a8d6cc71462085e91fc2594bed0247c91fb6f2097f7b2fc92e978ae4efecf
+size 45894

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.14, "n_eval_episodes": 100, "eval_datetime": "2022-06-29T13:12:50.904735"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.78, "n_eval_episodes": 100, "eval_datetime": "2022-06-29T14:29:25.019701"}