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: 7.32 +/- 2.51
+      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 sha256:9eb5834b6ac0e906eb33a6ffbe70c6462ad73c66c9c457f92a50981587524db1
-size 24589
+oid sha256:070ff40009e0160c81db11aac53cc8ce57b4979bb7e57b46204ebf9be1890a46
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0824dbb20965691facb65d86d7641afe31700cfccc3468317959992f2dc93a4
-size 89950
+oid sha256:c555acb4c1a1d664a4959416fd2f1f41ffee3c8694ff037653aad52424c0145e
+size 115014

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-24T00:16:12.175135"}
+{"env_id": "Taxi-v3", "mean_reward": 7.32, "n_eval_episodes": 100, "eval_datetime": "2023-11-26T00:23:29.180095"}