Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.00 +/- 0.00
+      value: 0.38 +/- 0.49
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff7feed42b2f99b5e73e6bec46cd959543127fb33ec7550c990b773408c940f
-size 24394
+oid sha256:ba888fba09a5df17fc7d11b3480a1bc3d4911c9cb0f496431e60252bb0d2a6b3
+size 2440

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319280cde8b330010bb15841fb3f53d2ff7abf83d0d064f15150809f12ef05aa
-size 142147
+oid sha256:d94e6f6276cd6a2e09e206dd284e03bbba937d3b901595b00913b3c36e22feed
+size 155428

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.0, "n_eval_episodes": 400, "eval_datetime": "2022-05-23T23:19:03.065884"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.38, "n_eval_episodes": 400, "eval_datetime": "2022-05-24T03:04:10.203247"}