Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Taxi-v3
+- Taxi-v3-4x4-no_slippery
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -11,11 +11,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Taxi-v3
-      type: Taxi-v3
+      name: Taxi-v3-4x4-no_slippery
+      type: Taxi-v3-4x4-no_slippery
     metrics:
     - type: mean_reward
-      value: 7.56 +/- 2.71
+      value: 1.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88927e6a1a6d985c0d9bcf156b5e5424e82d5b94009157b0806240ae860d1f38
-size 24570
+oid sha256:272f0ba9c2f33927c5c572abf8e913dc743b6ccbcad5fddc908aabccf5d29d75
+size 24601

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9184556eca4ef8804c0bb59426c374eb899da731826c82f6edb2b5f067606a06
-size 125582
+oid sha256:095acf0c554d1bdc846395181a69e802f20804f0f986bb1a63ec54540cb3a923
+size 31943

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-12-13T23:22:40.688121"}
+{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-12-14T00:06:25.874516"}