Guangxiang Zhu



Ph.D. in Computer Science
Deep Reinforcement Learning
@ Tsinghua University

Location Beijing, China
Email guangxiangzhu at outlook dot com
Github Github
linkedin LinkedIn

朱广翔


About Me

I am currently working at Baidu Inc. I received my Ph.D. from Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, headed by Prof. Andrew Yao (姚期智). My advisor is Prof. Chongjie Zhang (张崇洁) and I am the first graduate from Machine Intelligence Group . My research interests include Reinforcement Learning and Model-based Agent. My thesis is to improve the sample efficiency of the RL Agent via inductive models including object-oriented representation model, plannable world model, and associative memory model.

Selected Awards

  1. China Autonomous Agents and MultiAgent Systems Best Doctoral (top 1) Thesis (中国智能体与多智能体系统优秀博士论文奖), 2022.
  2. Beijing Excellent Doctoral Dissertation Award (北京市优秀博士学位论文), 2021.
  3. The award for Excellent Doctoral Dissertation of Tsinghua University (清华优秀博士学位论文), 2021.
  4. Top 10 Breakthroughs of 2018 in Chinese Bioinfomatics: Reconstructing spatial organizations of chromosomes through manifold learning [Zhu et al., 2018], awarded by Genomics, Proteomics and Bioinformatics (GPB).
    Reported by Tsinghua News
  5. National Scholarship (top 1%) at Tsinghua University (国家奖学金), 2019.
  6. Tsinghua Scholarship for Overseas Graduate Study, 2019.
  7. Champion of Shandong Division in the Fourth China "Internet Plus" Student Innovation and Entrepreneurship Competition, 2018.
  8. IIIS First-Class Scholarship, 2020.
  9. Toyota Second-Class Scholarship, 2020.
  10. Tsinghua-Baidu Future Star Third-Class Scholarship, 2018.
  11. Computing Accreditation for Professionals (Ranking: 5/372) certificated by China Computer Federation (CCF), 2015.

Publications

  1. Jianhao Wang, Wenzhe Li, Haozhe Jiang, Guangxiang Zhu, Siyuan Li, Chongjie Zhang.
    Offline Reinforcement Learning with Reverse Model-based Imagination.
    NeurIPS 2021: Advances in Neural Information Processing Systems.
    PDF
  2. Zhizhou Ren, Guangxiang Zhu, Hao Hu, Beining Han, Jianglun Chen, Chongjie Zhang.
    On the Estimation Bias in Double Q-Learning.
    NeurIPS 2021: Advances in Neural Information Processing Systems.
    PDF
  3. Yao Mu, Yuzheng Zhuang, Bin Wang, Guangxiang Zhu, Wulong Liu, Jianyu Chen, Ping Luo, Shengbo Eben Li, Chongjie Zhang, Jianye Hao.
    Model-Based Reinforcement Learning via Imagination with Derived Memory.
    NeurIPS 2021: Advances in Neural Information Processing Systems.
    PDF
  4. Hao Hu, Jianing Ye, Guangxiang Zhu, Zhizhou Ren and Chongjie Zhang.
    Generalizable Episodic Memory for Deep Reinforcement Learning.
    ICML 2021: International Conference on Machine Learning.
    PDF
  5. Wenbo Du, Tong Guo, Jun Chen, Biyue Li, Guangxiang Zhu and Xianbin Cao.
    Cooperative pursuit of unauthorized UAVs in urban airspace via multi-agent reinforcement learning.
    Transportation Research Part C: Emerging Technologies , 2021. [Impact Factor: 6.077]
    PDF
  6. Guangxiang Zhu*, Minghao Zhang*, Honglak Lee and Chongjie Zhang.
    Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning.
    NeurIPS 2020: Advances in Neural Information Processing Systems.
    PDF
  7. Guangxiang Zhu*, Zichuan Lin*, Guangwen Yang and Chongjie Zhang.
    Episodic Reinforcement Learning with Associative Memory.
    ICLR 2020: Eighth International Conference on Learning Representations.
    PDF
  8. Guangxiang Zhu*, Jianhao Wang*, Zhizhou Ren* and Chongjie Zhang.
    Object-Oriented Dynamics Learning through Multi-Level Abstraction.
    AAAI 2020: Thirty-Fourth AAAI Conference on Artificial Intelligence.
    PDF
  9. Jiangjiang Xia, Haochen Li, Yanyan Kang, Chen Yu, Lei Ji, Lue Wu, Xiao Lou, Guangxiang Zhu, Zaiwen Wang, Zhongwei Yan, Lizhi Wang, Jiang Zhu, Pingwen Zhang, Chongping Ji, Min Chen, Yingxin Zhang, Lihao Gao and Jiarui Han.
    Machine-Learning-Based Weather Support for 2022 Winter Olympics.
    Advances in Atmospheric Sciences, 2020. [Impact Factor: 2.583]
    PDF
  10. Tongyu Wang, Shangmei Zhao, Guangxiang Zhu and Haitao Zheng.
    A Machine Learning-Based Early Warning System for Systemic Banking Crises.
    Applied Economics incorporating Applied Financial Economics, 2020.
    PDF
  11. Abbas Ahmed, Xuan He, Bin Zhou, Guangxiang Zhu, Tszshan Ma, Juntao Gao, Michael Zhang and Jianyang Zeng.
    Integrating Hi-C and FISH data for modeling 3D organizations of chromosomes.
    Nature Communications, 2019, 10(1): 1-14. [Impact Factor: 12.343]
    PDF
  12. Siyuan Li, Fangda Gu, Guangxiang Zhu and Chongjie Zhang.
    Context-Aware Policy Reuse.
    AAMAS 2019: International Conference on Autonomous Agents and MultiAgent Systems.
    PDF
  13. Guangxiang Zhu, Zhiao Huang and Chongjie Zhang.
    Object-Oriented Dynamics Predictor.
    NeurIPS 2018: Advances in Neural Information Processing Systems.
    PDF
  14. Guangxiang Zhu, Wenxuan Deng, Hailin Hu, Rui Ma, Sai Zhang, Jinglin Yang, Jian Peng, Tommy Kaplan and Jianyang Zeng.
    Reconstructing spatial organizations of chromosomes through manifold learning.
    Nucleic Acids Research (NAR), 2018, 46(8), e50-e50. [Impact Factor: 11.561]
    PDF
  15. Jianbo Guo*, Guangxiang Zhu* and Jian Li.
    Generative Adversarial Mapping Networks.
    arXiv preprint, 2017
    PDF
  16. Zichuan Lin, Li Zhao, Jiang Bian, Guangxiang Zhu, Tao Qin and Guangwen Yang.
    Gamma Estimation for Variance Reduction in Deep Reinforcement Learning.
    Under Review, 2021.
    PDF

Experience and Services