Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- FrozenLake-v1-4x4
 - 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-v1-4x4
+      type: FrozenLake-v1-4x4
     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:dbe02b94899b96d323a2fda186080451aa5d1aac788a18481ab7d07648f25789
-size 913
+oid sha256:08b9f7a0b7774cd8a67d5dd467da56cf59042eb44374c6a7b16a8dc4f3335b2d
+size 901

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4efa3859d45c1b4c67ddde1e3027c95f915e3a4e64912b7a541660b9a97e2009
-size 31966
+oid sha256:cbb3bf2b5275bd8f52dc7ae6d030f33ce9d1ace89257f603b29a288c961a1c33
+size 32507

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-09-09T16:15:44.599987"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-09-09T16:24:06.476586"}