Upload of a new agent trained with QLearning on Taxi-v3

README.md

@@ -14,7 +14,7 @@ model-index:
       type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: -41.66 +/- 89.00
+      value: -79.10 +/- 102.89
       name: mean_reward
       verified: false
 ---

algorithm.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e0c3612ab9b2ab89ed93962a4dc65fbe244a22808af5041b08f75c6decd4e9
+oid sha256:fa72ba1c87eb0a831d38d8ac81519fdd0315d567609e0efbb9526503aa9c9d25
 size 24153

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab51c2cc3a9333c080d8ee7568a90c6d1fff492e08dc17457287cc78a03ade9
-size 75977
+oid sha256:8afcf34a19b099bea6216762dd90d9222564ba6c59762aac8c55bf90c957deec
+size 473938

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": -41.66, "n_eval_episodes": 50, "eval_datetime": "2023-12-08T14:03:24.962105"}
+{"env_id": "Taxi-v3", "mean_reward": -79.1, "n_eval_episodes": 50, "eval_datetime": "2023-12-12T14:28:31.435822"}

system.json

@@ -1 +1 @@
-{"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.9.13", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.1+cpu", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}
+{"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.10.8", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.1+cpu", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}