Upload . with huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- Taxi-v3
 - 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: Taxi-v3
+      type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 7.56 +/- 2.71
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389d366724bb1240d90d8d7a5cbca8e9af6d07482fe8babe030aa176111bcc48
-size 914
+oid sha256:0b8773022dbd2e150a05c2c8cf54c303433796d7d3e35873bc7a4fcb48913e12
+size 24575

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
-size 31943
+oid sha256:9ecbf3004921fc3a0b31dbe10798852f6968daf4891aad0cae82264a7ce9b44b
+size 125867

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2023-03-06T19:59:31.185790"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2023-03-06T23:34:32.173700"}