Yaqi Duan

Welcome to my homepage! I am an Assistant Professor in the Department of Technology, Operations, and Statistics at Stern School of Business at New York University. My primary research interests lie in machine learning, particularly statistical aspects of reinforcement learning.

I graduated with a Ph.D. degree from the Department of Operations Research and Financial Engineering at Princeton University in 2022. From 2022 to 2023, I was a postdoctoral researcher at the Laboratory for Information & Decision Systems at Massachusetts Institute of Technology, working with Professor Martin J. Wainwright. Prior to my doctoral studies, I received a B.S. in Mathematics from Peking University.

📧 yaqi.duan [At] stern [Dot] nyu [Dot] edu

📬 KMC 8-54, 44 West 4th Street, New York, NY 10012

News

Jan 11, 2024 New paper Taming “data-hungry” reinforcement learning? Stability in continuous state-action spaces posted on arXiv.
Dec 17, 2023 Paper Adaptive and robust multi-task learning accepted by the Annals of Statistics.
Aug 1, 2023 I’ve joined NYU Stern School of Business as an Assistant Professor in the Department of Technology, Operations, and Statistics. Thrilled to embark on this new academic journey!
Nov 9, 2022 New paper Policy evaluation from a single path: Multi-step methods, mixing and mis-specification posted on arXiv.
Oct 31, 2022 I am honored to receive the 2023 IMS Lawrence D. Brown Ph.D. Student Award.

Selected publications

  1. Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
    Duan, Yaqi, and Wainwright, Martin J.
    arXiv Preprint 2024
  2. Policy evaluation from a single path: Multi-step methods, mixing and mis-specification
    Duan, Yaqi, and Wainwright, Martin J.
    arXiv Preprint 2022
  3. Optimal policy evaluation using kernel-based temporal difference methods
    Duan, Yaqi, Wang, Mengdi, and Wainwright, Martin J.
    arXiv Preprint 2021
  4. Minimax-optimal off-policy evaluation with linear function approximation
    Duan, Yaqi, and Wang, Mengdi
    International Conference on Machine Learning (ICML) 2020