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: 0.76 +/- 0.43
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7899d21d95f138e88d1e6e119d54aaa7a56b352fce0c58d02846273216a35a99
-size 914
+oid sha256:81dc07000153e14e4a3007207613814aa2aa5d98e24743c36c822ae28ae87ca0
+size 902

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
-size 31943
+oid sha256:a1c10a8aa6821c36b64608d1dcadee5d80d4ea61ae87465413bce6a8c86faac6
+size 43052

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-10-08T15:51:57.782108"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.76, "n_eval_episodes": 100, "eval_datetime": "2022-10-08T15:55:24.034598"}