Jiayu Chen

@dase.hku.hk

Data and Systems Engineering
The University of Hong Kong

Jiayu Chen


                           Download Compact PDF  
https://researchid.co/jiayu_chen
Jiayu Chen is an Assistant Professor in the Department of Data and Systems Engineering at The University of Hong Kong. From 2024 to 2025, he was a Postdoctoral Fellow at the School of Computer Science, Carnegie Mellon University. Dr. Chen received his Ph.D. in Industrial Engineering and Operations Research from Purdue University in 2024, and his B.Eng. from Peking University in 2020. His research focuses on reinforcement learning and robotics. Dr. Chen has published as first author in top venues such as NeurIPS, ICML, IJCAI, ICRA, and IEEE Transactions, and has received prestigious honors including the Oracle Research Award and the Purdue Research Grant.

EDUCATION

2016 - 2020: Peking University, Bachelor of Engineering;
2020 - 2024: Purdue University, PhD in Industrial Engineering;

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Engineering

FUTURE PROJECTS

Offline Reinforcement Learning for Controllable Nuclear Fusion

Please check: https://agentic-intelligence-lab.org/files/research_topics.pdf


Applications Invited
students

Continual Reinforcement Learning for Humanoid Robotic Control

Please check: https://agentic-intelligence-lab.org/files/research_topics.pdf


Applications Invited
students

Learning-based Ego-centric Evolution within a Multi-agent System

Please check: https://agentic-intelligence-lab.org/files/research_topics.pdf


Applications Invited
students
457

Scholar Citations

12

Scholar h-index

16

Scholar i10-index

RECENT SCHOLAR PUBLICATIONS

  • Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
    Y Xu, J Zhang, X Wu, Z Zhou, J He, J Chen
    arXiv preprint arXiv:2605.08681 , 2026
    2026
  • Offline Reinforcement Learning for Rotation Profile Control in Tokamaks
    R Sonker, HJF Kaga, J Chen, A Rothstein, I Char, R Shousha, E Kolemen, ...
    arXiv preprint arXiv:2605.05857 , 2026
    2026
  • Malinzero: Efficient low-dimensional search for mastering complex multi-agent planning
    S Tang, J Chen, T Lan
    Advances in Neural Information Processing Systems 38, 75248-75278 , 2026
    2026
    Citations: 11
  • AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
    L Fan, Z Xu, C Cao, W Zhang, M Yuan, J Chen
    arXiv preprint arXiv:2604.11135 , 2026
    2026
    Citations: 1
  • CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
    Z Ding, X Lai, W Chen, XP Zhang, J Chen
    arXiv preprint arXiv:2604.07712 , 2026
    2026
  • Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization (Student Abstract)
    L Xu, J Chen
    Proceedings of the AAAI Conference on Artificial Intelligence 40 (48), 41433 … , 2026
    2026
  • Explore to Learn: Latent Exploration Through Disentangled Synergy Patterns for Reinforcement Learning in Overactuated Control
    Y Wang, K Zhao, X Li, Y Li, J Chen, S Morad
    Proceedings of the AAAI Conference on Artificial Intelligence 40 (31), 26670 … , 2026
    2026
    Citations: 1
  • DSAP: Enhancing Generalization in Goal-Conditioned Reinforcement Learning
    Y Wang, K Zhao, M Yang, Y Li, F Liu, J Chen
    Proceedings of the AAAI Conference on Artificial Intelligence 40 (31), 26679 … , 2026
    2026
    Citations: 1
  • Atomvla: Scalable post-training for robotic manipulation via predictive latent world models
    X Sun, Z Xu, C Cao, Z Liu, Y Sun, J Pang, R Zhang, Z Yang, K Pang, D He, ...
    arXiv preprint arXiv:2603.08519 , 2026
    2026
    Citations: 3
  • Vision Transformers that Never Stop Learning
    C Sun, M Yuan, S Wang, J Chen
    arXiv preprint arXiv:2603.07787 , 2026
    2026
  • Plasticine: Accelerating research in plasticity-motivated deep reinforcement learning
    M Yuan, Q Wang, G Ma, B Li, X Jin, Y Wang, X Yang, W Zeng, D Tao, ...
    arXiv preprint arXiv:2504.17490 , 2026
    2026
    Citations: 3
  • Offline Discovery of Interpretable Skills from Multi-Task Trajectories
    C Zhu, M Vanniasinghe, J Chen, CG Lee
    arXiv preprint arXiv:2602.01018 , 2026
    2026
  • Continual Policy Distillation from Distributed Reinforcement Learning Teachers
    Y Li, Q He, M Yuan, WT Chen, J Schneider, J Chen
    arXiv preprint arXiv:2601.22475 , 2026
    2026
  • TURBO-RL: turbulence mitigation using reinforcement learning for severe optical aberrations
    H Choi, J Chen, V Aggarwal, Z Jacob
    Journal of the Optical Society of America A 43 (2), 236-240 , 2026
    2026
  • Verlog: An Efficient Synchronized Multi-turn RL Framework for LLM Agents
    W Chen, J Chen, H Zhu, F Tajwar, R Salakhutdinov, J Schneider
    2026
  • Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning
    A Venugopal, J Chen, X Wu, C Zheng, B Eysenbach, J Schneider
    The Fourteenth International Conference on Learning Representations , 2026
    2026
  • A survey of behavior foundation model: Next-generation whole-body control system of humanoid robots
    M Yuan, T Yu, W Ge, X Yao, D Li, H Wang, J Chen, B Li, W Zhang, ...
    IEEE transactions on pattern analysis and machine intelligence , 2025
    2025
    Citations: 12
  • RoboTidy: A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action
    X Sun, R Zhang, K Pang, B Miao, Y Tan, Z Yang, M Li, J Chen
    arXiv preprint arXiv:2511.14161 , 2025
    2025
    Citations: 1
  • Rack Position Optimization in Large-Scale Heterogeneous Data Centers
    CL Chen, J Chen, T Lan, Z Zhao, H Dong, V Aggarwal
    International Conference on Automated Planning and Scheduling , 2025
    2025
  • ME-IGM: Individual-Global-Max in Maximum Entropy Multi-Agent Reinforcement Learning
    JS Wentse Chen, Yuxuan Li, Shiyu Huang, Jiayu Chen
    arXiv preprint arXiv:2406.13930v3 , 2025
    2025

MOST CITED SCHOLAR PUBLICATIONS

  • Decision making for autonomous driving via augmented adversarial inverse reinforcement learning
    P Wang, D Liu, J Chen, H Li, CY Chan
    2021 IEEE International Conference on Robotics and Automation (ICRA), 1036-1042 , 2021
    2021
    Citations: 90
  • Deepfreight: A model-free deep-reinforcement-learning-based algorithm for multi-transfer freight delivery
    J Chen, AK Umrawal, T Lan, V Aggarwal
    Proceedings of the International Conference on Automated Planning and … , 2021
    2021
    Citations: 30
  • Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions
    J Chen, B Ganguly, Y Xu, Y Mei, T Lan, V Aggarwal
    Transactions on Machine Learning Research , 2024
    2024
    Citations: 29
  • Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs
    J Chen, J Chen, T Lan, A Vaneet
    Proceedings of the 36th Conference on Neural Information Processing Systems … , 2022
    2022
    Citations: 29
  • Multi-task Hierarchical Adversarial Inverse Reinforcement Learning
    J Chen, D Tamboli, T Lan, V Aggarwal
    Proceedings of the 40th International Conference on Machine Learning, 4895-4920 , 2023
    2023
    Citations: 26
  • Option-aware adversarial inverse reinforcement learning for robotic control
    J Chen, T Lan, V Aggarwal
    arXiv preprint arXiv:2210.01969 , 2022
    2022
    Citations: 25
  • Learning multiagent options for tabular reinforcement learning using factor graphs
    J Chen, J Chen, T Lan, V Aggarwal
    IEEE Transactions on Artificial Intelligence 4 (5), 1141-1153 , 2022
    2022
    Citations: 25
  • Hierarchical adversarial inverse reinforcement learning
    J Chen, T Lan, V Aggarwal
    IEEE Transactions on Neural Networks and Learning Systems 35 (12), 17549-17558 , 2023
    2023
    Citations: 24
  • Learning-based two-tiered online optimization of region-wide datacenter resource allocation
    CL Chen, H Zhou, J Chen, M Pedramfar, T Lan, Z Zhu, C Zhou, PM Ruiz, ...
    IEEE Transactions on Network and Service Management 22 (1), 572-581 , 2024
    2024
    Citations: 23
  • Reinforced sequential decision-making for sepsis treatment: The posnegdm framework with mortality classifier and transformer
    D Tamboli, J Chen, KP Jotheeswaran, D Yu, V Aggarwal
    IEEE Journal of Biomedical and Health Informatics 28 (5), 3114-3122 , 2024
    2024
    Citations: 15
  • A unified algorithm framework for unsupervised discovery of skills based on determinantal point process
    J Chen, V Aggarwal, T Lan
    Advances in Neural Information Processing Systems 36, 67925-67947 , 2023
    2023
    Citations: 13
  • A survey of behavior foundation model: Next-generation whole-body control system of humanoid robots
    M Yuan, T Yu, W Ge, X Yao, D Li, H Wang, J Chen, B Li, W Zhang, ...
    IEEE transactions on pattern analysis and machine intelligence , 2025
    2025
    Citations: 12
  • Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
    S Ganesh, J Chen, G Thoppe, V Aggarwal
    Transactions on Machine Learning Research , 2024
    2024
    Citations: 12
  • Malinzero: Efficient low-dimensional search for mastering complex multi-agent planning
    S Tang, J Chen, T Lan
    Advances in Neural Information Processing Systems 38, 75248-75278 , 2026
    2026
    Citations: 11
  • Order-optimal global convergence for actor-critic with general policy and neural critic parametrization
    S Ganesh, J Chen, WU Mondal, V Aggarwal
    The 41st Conference on Uncertainty in Artificial Intelligence , 2025
    2025
    Citations: 10
  • Multi-agent Deep Covering Option Discovery
    J Chen, M Haliem, T Lan, V Aggarwal
    ICML Reinforcement Learning for Real Life Workshop , 2021
    2021
    Citations: 10
  • Learning explainable stock predictions with tweets using mixture of experts
    W Xu, D Xiang, R Wang, Y Hu, L Zhang, J Chen, Z Lu
    arXiv preprint arXiv:2507.20535 , 2025
    2025
    Citations: 9
  • Variational offline multi-agent skill discovery
    J Chen, T Lan, V Aggarwal
    arXiv preprint arXiv:2405.16386 , 2024
    2024
    Citations: 9
  • Bayes adaptive monte carlo tree search for offline model-based reinforcement learning
    J Chen, L Xu, W Chen, J Schneider
    arXiv preprint arXiv:2410.11234 , 2024
    2024
    Citations: 7
  • Context-lite Multi-turn Reinforcement Learning for LLM Agents
    W Chen, J Chen, H Zhu, J Schneider
    ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models , 2025
    2025
    Citations: 6