Yunpeng Qing

College of Computer Science and Technology, Zhejiang University

my.jpeg

Hangzhou, China

Hello! I am Yunpeng Qing, a Second-year Ph.D. student in the Visual Intelligence and Pattern Analysis (VIPA) Lab @ ZheJiang University (ZJU), advised by Professor Mingli Song. In the past, I have received my B.E. degree from the College of Computer Science and Technology, Zhejiang University in 2023.6.

Currently my reseach interests lie in Reinforcement Learning, especially Offline Reinforcement Learning. My researching goal is to create a robust and reliable general framework for agent to effectively utilize sequantial decision-making informations data for behavior improvement. Towards this goal, my prior work has been dedicated to devising methods that facilitate the application of reinforcement learning algorithms on a variety of static datasets.

Please always feel free to contact me via yunpeng.qing.cs@gmail.com if you have any questions, are interested in collaborating, or just want to chat.

[Google Scholar]    [Email]    [GitHub]   

news

Jan 8, 2025 One paper is accepted by IEEE TITS.
Dec 20, 2024 One paper is accepted by AAMAS 2025.
Nov 16, 2024 One paper is accepted by KDD 2025 ADS Track.
Sep 26, 2024 One paper is accepted by NeurIPS 2024.
May 17, 2024 One paper is accepted by KDD 2024.

selected publications

  1. NeurIPS
    A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
    Yunpeng Qing, shunyu Liu, Jingyuan Cong, and 3 more authors
    NeurIPS, 2024
    HTML Code
  2. IEEE TITS
    Curricular Subgoals for Inverse Reinforcement Learning
    Shunyu Liu*, Yunpeng Qing*, Shuqi Xu, and 6 more authors
    IEEE Transaction on Intelligent Transportation Systems, 2025
    HTML Code
  3. Review in CSUR
    A survey on explainable reinforcement learning: Concepts, algorithms, challenges
    Yunpeng Qing, Shunyu Liu, Jie Song, and 2 more authors
    arXiv, 2023
    HTML Code