Upload folder using huggingface_hub

README.md

@@ -7,16 +7,17 @@ tags:
 model-index:
 - name: q-Taxi-v3
   results:
-  - metrics:
-    - type: mean_reward
-      value: 7.56 +/- 2.71
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: Taxi-v3
       type: Taxi-v3
+    metrics:
+    - type: mean_reward
+      value: 7.56 +/- 2.71
+      name: mean_reward
+      verified: false
 ---
 
   # **Q-Learning** Agent playing **Taxi-v3**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f149beb012f3db5e89fa5a786614141765db164d8c8b7966d789e7df02148c56
-size 24589
+oid sha256:03a16cc292b919bf3cd3d2873b422b3882bbafe02aecb9463ae57cc5760dc801
+size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158226139ffd6765234fa3ccbd01f8ec00d913bfb780f347a42d242a4fd05a5d
-size 126478
+oid sha256:86cc99519c677febcfa31749bd181ce895267a1eb374b798d1c69ce95a7c9b64
+size 122869

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-07-25T18:38:33.818766"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2024-10-21T08:27:48.059078"}