Pushi Zhang (张蒲石)

Researcher, Microsoft Research

Google Scholar | Email: pushizhang@microsoft.com

News

Short Bio

I’m a researcher in the Machine Learning Group at Microsoft Research (Asia), currently leading the project of RL for autonomous game agent at Microsoft Research in collaboration with XBox team. My current research interests include reinforcement learning and foundation models for embodied AI.

Publications

  1. IG-Net: Image-Goal Network for Offline Visual Navigation on A Large-Scale Game Map
    Baiting Zhu*, Pushi Zhang*, Xin-Qiang Cai*, Li Zhao, Masashi Sugiyama, Jiang Bian.
    NeurIPS 2023 Robot Learning Workshop [demo] [pdf]
  2. Distributional Pareto-Optimal Multi-Objective Reinforcement Learning
    Xin-Qiang Cai*, Pushi Zhang*, Li Zhao, Jiang Bian, Masashi Sugiyama, Ashley J. Llorens.
    NeurIPS 2023 [code] [pdf]
  3. Asking Before Action: Gather Information in Embodied Decision Making with Language Models
    Xiaoyu Chen, Shenao Zhang, Pushi Zhang, Li Zhao, Jianyu Chen.
    Arxiv 2023.5 [pdf]
  4. An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
    Xiaoyu Chen, Xiangming Zhu, Yufeng Zheng, Pushi Zhang, Li Zhao, Wenxue Cheng, Peng Cheng, Yongqiang Xiong, Tao Qin, Jianyu Chen, Tie-Yan Liu.
    NeurIPS 2022 [pdf]
  5. Distributional Reinforcement Learning for Multi-Dimensional Reward Functions
    Pushi Zhang, Xiaoyu Chen, Li Zhao, Wei Xiong, Tao Qin, Tie-Yan Liu.
    NeurIPS 2021 [code] [pdf]
  6. Independence-aware Advantage Estimation
    Pushi Zhang, Li Zhao, Guoqing Liu, Jiang Bian, Minlie Huang, Tao Qin, Tie-Yan Liu.
    IJCAI 2021 [pdf]
  7. Demonstration Actor Critic
    Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu.
    Neurocomputing 2021 [pdf]

About Myself

I love research and hope to do the research work that is beneficial to the world.

Last update: 2024.9.20