Zhengpeng Xie

prof_pic.jpg

Hi there! I’m a student who is interested in deep reinforcement learning (DRL). My recent research focuses on designing theoretically sound policy gradient algorithms and improving their generalization performance.

I am looking for highly motivated assistant professors. If you are working at a university ranked in the top 50 of the QS Rankings and have a reasonable background in RL, feel free to contact me through zhengpengxie@hkust-gz.edu.cn!

news

May 01, 2025 Simple Policy Optimization has been accepted to ICML 2025! :smile:

selected publications

  1. Conference
    Simple Policy Optimization
    Zhengpeng Xie, Qiang Zhang, Fan Yang, Marco Hutter, and Renjing Xu
    In Forty-second International Conference on Machine Learning, 2025
  2. Preprint
    Representation Convergence: Mutual Distillation is Secretly a Form of Regularization
    Zhengpeng Xie, Jiahang Cao, Qiang Zhang, Jianxiong Zhang, Changwei Wang, and Renjing Xu
    2025