Researcher · Information Science

Gongpu Chen陈功谱

I am a postdoctoral researcher at Imperial College London, working with Prof. Deniz Gündüz. I obtained my PhD degree from The Chinese University of Hong Kong in 2023, under the supervision of Prof. Soung Chang Liew. Prior to that, I obtained my Master’s degree from Southeast University in 2019 and my Bachelor’s degree from the University of Electronic Science and Technology of China in 2016.

Gongpu Chen

Research Associate
Imperial College London

Google Scholar CV / Résumé

Research

My research interests broadly lie at the intersection of communication, control, and machine learning. At the core of my work is a fundamental question: How does the interplay between information and control/decision-making shape the performance, efficiency, and robustness of intelligent cyber-physical systems? I explore this question from both communication and control perspectives, drawing on tools from information theory, control theory, Markov decision processes, reinforcement/machine learning, and optimization.

🔒
Integrated Communication and Control
The control plant itself can serve as the communication channel, enabling agents to exchange information without any explicit communication channel. Under this framework, communication is coupled with control not only at the level of the message, but also at the level of the channel.
Learn more →
⚡
Control Under Communication Constraint
Communication-induced partial observability has a distinctive information structure, making the problem a tractable and practically important subclass of partially observable Markov decision process (POMDP).
Learn more →
🧠
Sensing and Communication for Control
A defining feature of cyber-physical systems is the tight coupling between the cyber and physical spaces. As a result, sensing and communication are not ends in themselves, but rather means of achieving the control objective.
Learn more →
📡
Restless Multi-arm Bandits (RMAB)
RMABs are a widely used framework for sequential decision-making, with applications in many fields. Their solution, however, is hindered by the exponentially growing state space and the combinatorial action space. As a result, designing efficient planning and learning algorithms for RMABs remains a long-standing challenge.
Learn more →

Publications

15 papers
2026
GINO-Q: Learning an asymptotically optimal index policy for restless multi-armed bandits
Gongpu Chen, Soung Chang Liew, and Deniz Gündüz
AAAI 2026 · Singapore
DOI arXiv Slides Talk
Oral Presentation Reinforcement Learning Restless Multi-armed Bandits
2026
Intermittently Observable Markov Decision Processes
Gongpu Chen and Soung Chang Liew
IEEE Transactions on Automatic Control · Vol. 71, no. 2, pp. 1054-1069
DOI arXiv
MDP Planning
2025
Implicit Communication in Linear Quadratic Gaussian Control Systems
Gongpu Chen and Deniz Gündüz
arXiv:2509.16146
arXiv Slides
Information Theory LQG Control
2025
Joint control and communication scheduling in multi-agent systems with two receivers
Edoardo David Santi, Gongpu Chen, and Deniz Gündüz
Asilomar 2025 · Pacific Grove, CA, USA
DOI
Multi-agent MDP
2025
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
Haotian Wu, Gongpu Chen, Pier Luigi Dragotti, and Deniz Gündüz
ICML 2025 · Vancouver, Canada
DOI arXiv Slides
Spotlight Image Compression Implicit Neural Representation Lottery Ticket Hypothesis
2025
Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes
Haotian Wu*, Gongpu Chen*, and Deniz Gündüz (*equal contribution)
ICLR 2025 · Singapore
DOI arXiv Slides
MDP Information Theory Channel Coding
2025
Covert Adversarial Actuators in Finite MDPs
Edoardo David Santi, Gongpu Chen, Gongpu Chen, Deniz Gündüz, Asaf Cohen
ISIT 2025 · Ann Arbor, MI, USA
DOI arXiv
MDP Hypothesis Testing Covert Attack
2023
An index policy for minimizing the uncertainty-of-information of Markov sources
Gongpu Chen and Soung Chang Liew
IEEE Transactions on Information Theory, vol. 70, no. 1, pp. 698-721
DOI arXiv Slides
Communication Network Information Freshness Restless Multi-armed Bandits
2023
Periodic Transmissions in Random Access Networks: Stressed Period and Delay
Gongpu Chen, Lihao Zhang, and Soung Chang Liew
IEEE Transactions on Communications, vol. 71, no. 7, pp. 4119-4132,
DOI
Random Access Network Queueing Theory Communication for Control
2022
Uncertainty-of-Information Scheduling: A Restless Multiarmed Bandit Framework
Gongpu Chen, Soung Chang Liew, and Yulin Shao
IEEE Transactions on Information Theory, vol. 68, no. 9, pp. 6151-6173
DOI arXiv
Communication Network Information Freshness Restless Multi-armed Bandits
2021
Joint scheduling and channel allocation for Kalman filtering over multihop WirelessHART networks
Gongpu Chen, Xianghui Cao, and Jiong Jin
IEEE Transactions on Industrial Informatics, vol. 17, no. 5, pp. 3555-3565
DOI
Industrial Wireless Network Communication for Control
2019
A Consensus-State-Aware Adaptive Algorithm for Tuning CSMA Parameters in Multi-Agent Networks
Mengdan Lei, Xianghui Cao, Gongpu Chen, and Changyin Sun
ISIE 2019 · Vancouver, BC, Canada
DOI
Multi-agent Random Access Network
2019
Joint Scheduling and Channel Allocation for End-to-End Delay Minimization in Industrial WirelessHART Networks
Gongpu Chen, Xianghui Cao, Lu Liu, Changyin Sun, and Yu Cheng
IEEE Internet of Things Journal, vol. 6, no. 2, pp. 2829-2842
DOI
Industrial Wireless Network Network Optimization
2019
An Auction-based Channel Allocation and Power Control Algorithm for V2V Communications in VANETs
Yuxian Tao and Gongpu Chen
YAC 2019 · Jinzhou, China
DOI
Wireless Network Network Optimization
2018
Channel List Selection Based on Quality Prediction in WirelessHART Networks
Gongpu Chen, Rui Ma, Mengdan Lei, and Xianghui Cao
Journal of Communications and Information Networks, vol. 3, no. 3, pp. 49-56
DOI
Industrial Wireless Network Network Optimization

Miscellaneous

调心

闭门读佛书

菩提般若之智，世人本自有之

查看详情
溪山

出门寻山水

文词带烟霞，行事绝尘俗

查看详情
雪景

拾云随笔

读书人念头通达，无执无妄，便胜过风流无数

查看详情
渔父

述往思来

人有好古之心，便能时常冷却被俗世浮华勾起的焦灼心肠

查看详情

Contact

I'm always happy to chat about research, potential collaborations, or opportunities. Feel free to reach out via email. I typically respond within a few days.

Curriculum Vitae

My CV includes my full publication list, academic appointments, teaching experience, and service record.

Download CV (PDF)