Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.67 +/- 0.47
+      value: 0.76 +/- 0.43
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8ba2c636efc613cd6325be87b8a1d8e8dc51e08e04be6be52ad929bd276c8c
-size 925
+oid sha256:f27f24a5f78070b12d1673a38a010d215c1d528995031e8d95c2bc14a862dbfc
+size 924

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc5db6318198c37d9f35385f42aee555482189287409d5a0dd20f13cc2e22ab4
-size 36243
+oid sha256:de0f5790dd4f40d106523a7eb4ec841a0f08de42ecbbbdde8df60b1fad6d5fac
+size 41162

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.673, "n_eval_episodes": 1000, "eval_datetime": "2022-06-02T19:49:13.226939"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.76, "n_eval_episodes": 100, "eval_datetime": "2022-06-02T19:56:44.436615"}