Xihuai Wang's Page

APEX Lab, Shanghai Jiao Tong University.

portrait.png

Shanghai, China

Xihuai Wang is currently a Ph.D. candidate at Shanghai Jiao Tong University, supervised by Prof. Weinan Zhang and Prof. Ying Wen. He is a member of SJTU-Apex Group and a member of SJTU-MARL Group leaded by Prof. Ying Wen, and is also selected into Wenjun Wu Honored Ph.D. Class in 2020. Xihuai earned his B.Eng. in Computer Science and Technology at School of Computer Science and Engineering, Sun Yat-sen University in 2020.

Xihuai’s research interests include Decision-making and Multi-agent System. Specifically, he is now focusing on

  • Multi-agent Decision-making in Cooperative Scenarios, especially
    • Efficiency of Cooperative Multi-agent Reinforcement Learning;
    • Zero-shot Generalization Ability in Cooperative Multi-agent Systems.
  • Large Language Models for Decision-making.

news

Aug 8, 2023 Give a talk about cooperative multi-agent reinforcement learning (Coordinate Agents vis Policy Optimization) at RLChina.
Mar 25, 2023 Our work about policy optimization in cooperative multi-agent scenarios Order Matters: Agent-by-agent Policy Optimization was accepted by ICLR 2023.

selected publications

  1. ZSC Evaluation
    Quantifying Zero-shot Coordination Capability with Behavior Preferring Partners
    Xihuai Wang, Shao Zhang, Wenhao Zhang, Wentao Dong, Jingxiao Chen, Ying Wen, and Weinan Zhang
    Preprint, 2023
    PDF
  2. A2PO
    Order Matters: Agent-by-agent Policy Optimization
    Xihuai Wang, Zheng Tian, Ziyu Wan, Ying Wen, Jun Wang, and Weinan Zhang
    In The Eleventh International Conference on Learning Representations , 2023
    PDF Code
  3. AORPO
    Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts
    Weinan Zhang, Xihuai Wang, Jian Shen, and Ming Zhou
    IJCAI, 2021
    PDF Code