Hao Hu



Ph.D. Candidate in Computer Science
IIIS, Tsinghua University
Beijing, China
Email Email
Github Github
Linkedin Linkedin
CV CV / 中文简历
gscholar Google Scholar

About

I am currently a Ph.D. candidate working with Prof. Chongjie Zhang and Prof. Yang Gao at Institute for Interdisciplinary Information Sciences, Tsinghua University, headed by Prof. Andrew Yao. I received my B.Sc. degree in Theoretical and Applied Mechanics from Peking University in 2019, with a double major in Computer Science. During my Ph.D., I was fortunate to visit Northwestern University and work with Prof. Zhaoran Wang .

My primary research goal is to build intelligent and autonomous agents and deepen the understanding of our own intelligence. Toward this goal, my research interest has been focused on designing algorithms for decision-making in a principled and data-driven approach, which are essential for agents to act and learn effectively in complex environments. Current directions I am working on include offline reinforcement learning, reinforcement learning with foundation models, and reinforcement learning theory.

Please feel free to contact me if you are interested in collaborating with me.

Publications and Preprints

  1. Bayesian Design Principles for Offline-to-Online Reinforcement Learning
    Hao Hu*, Yiqin Yang*, Jianing Ye, Chengjie Wu, Ziqing Mai, Yujing Hu, Tangjie Lv, Changjie Fan, Qianchuan Zhao, Chongjie Zhang
    Forty-first International Conference on Machine Learning (ICML), 2024
    PDF | Code
  2. Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
    Zhihan Liu*, Hao Hu*, Shenao Zhang*, Hongyi Guo, Shuqi Ke, Boyi Liu, Zhaoran Wang
    Forty-first International Conference on Machine Learning (ICML), 2024
    NeurIPS Workshop on Foundation Models for Decision Making, 2023
    PDF | Code | Project Page
  3. Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale Planners
    Chengjie Wu*, Hao Hu*, Yiqin Yang, Ning Zhang, Chongjie Zhang
    Forty-first International Conference on Machine Learning (ICML), 2024
    PDF | Code
  4. Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets
    Yihuan Mao, Chengjie Wu, Xi Chen, Hao Hu, Ji Jiang, Tianze Zhou, Tangjie Lv, Changjie Fan, Zhipeng Hu, Yi Wu, Yujing Hu, Chongjie Zhang
    The Twelfth International Conference on Learning Representations (ICLR), 2024
    PDF
  5. One Objective to Rule Them All: A Maximization Objective Fusing Estimation and Planning for Exploration
    Zhihan Liu* Miao Lu* Wei Xiong* Han Zhong, Hao Hu, Shenao Zhang, Sirui Zheng, Zhuoran Yang, Zhaoran Wang
    Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS Spotlight), 2023
    PDF | Code
  6. Unsupervised Behavior Extraction via Random Intent Priors
    Hao Hu*, Yiqin Yang* Jianing Ye, Ziqing Mai, Chongjie Zhang
    Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023
    PDF | Code
  7. What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?
    Rui Yang, Yong Lin, Xiaoteng Ma, Hao Hu , Chongjie Zhang, Tong Zhang
    Eleventh International Conference on Learning Representations (ICLR), 2023
    PDF | Code
  8. The Provable Benefit of Unsupervised Data Sharing for Offline Reinforcement Learning
    Hao Hu*, Yiqin Yang*, Qianchuan Zhao, Chongjie Zhang
    Eleventh International Conference on Learning Representations (ICLR), 2023
    PDF | Code
  9. Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery
    Yiqin Yang*, Hao Hu*, Wenzhe Li*, Siyuan Li, Jun Yang, Qianchuan Zhao, Chongjie Zhang
    Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023
    PDF | Code
  10. On the Role of Discount Factor in Offline Reinforcement Learning
    Hao Hu*, Yiqin Yang*, Qianchuan Zhao, Chongjie Zhang
    International Conference on Machine Learning (ICML), 2022
    PDF | Code
  11. Offline Reinforcement Learning with Value-based Episodic Memory
    Xiaoteng Ma*, Yiqin Yang*, Hao Hu*, Qihan Liu, Jun Yang, Chongjie Zhang, Qianchuan Zhao, Bin Liang
    Tenth International Conference on Learning Representations (ICLR), 2022
    PDF | Code
  12. On the Estimation Bias in Double Q-Learning
    Zhizhou Ren, Guangxiang Zhu, Hao Hu, Beining Han, Jianglun Chen, Chongjie Zhang
    Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS), 2021
    PDF | Code
  13. Generalizable Episodic Memory for Deep Reinforcement Learning
    Hao Hu, Jianing Ye, Zhizhou Ren, Guangxiang Zhu, and Chongjie Zhang
    International Conference on Machine Learning (ICML), 2021
    PDF | Code
  14. MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
    Jin Zhang*, Jianhao Wang*, Hao Hu, Tong Chen, Yingfeng Chen, Changjie Fan, Chongjie Zhang
    International Conference on Machine Learning (ICML), 2021
    PDF | Code
  15. Query-Efficient Offline Preference-Based Reinforcement Learning via In-Dataset Exploration
    Hao Hu*, Yiqin Yang*, Shuai Wang, Bo Liu, Yang Gao, Chongjie Zhang
    Under Review
    PDF

Experience

Services

Selected Talks

Education