custom Q-learning for 4x4 slippery

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.04 +/- 0.20
+      value: 0.80 +/- 0.40
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2a7fd3b60527236fddb53cc3556f09e4d44343d6714583bbdce0b2c87339980
+oid sha256:c7fe564cb148e8914a739db0b806e1795d932a449ea1f7ee0c842badd0758777
 size 921

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4854e1d739c266ca02cc2b5d6b82646d8bd81784fe6c993114f32d53c3d77598
-size 30187
+oid sha256:d7ddba8e8e3d86fd271aaeeb804ed314d2dee03d5c8d3c5e562b729cc76e3b1f
+size 34555

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.04, "n_eval_episodes": 100, "eval_datetime": "2022-05-21T14:54:59.250846"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.8041237113402062, "n_eval_episodes": 100, "eval_datetime": "2022-05-21T15:06:44.507392"}