Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- FrozenLake-v1-8x8-no_slippery
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -11,11 +11,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1-4x4-no_slippery
-      type: FrozenLake-v1-4x4-no_slippery
+      name: FrozenLake-v1-8x8-no_slippery
+      type: FrozenLake-v1-8x8-no_slippery
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 0.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1db87a8412cd711221a8b8dc07a05da3b68467f02d1c6d5f67488184c4cad9
-size 933
+oid sha256:3fd464ca0e05ae968ec59afc1cd1f5b3622147216bc80eeb8a419cd44b3f301d
+size 2469

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92561e624f5c82daa14ee53ea0ff19f5081bc706fc7b0a4123cf6997969184d
-size 36192
+oid sha256:cb0116ddd1fcab2622a7458ceee60e1f412916dd93b3b5b2be2e15f7d0367cdf
+size 135865

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2024-11-12T14:07:58.249934"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2024-11-12T14:18:29.103327"}