Tianpeng Zhang

Harvard University, Hangzhou Normal University

Papers

Total Citations

H-Index

About

Tianpeng Zhang is an emerging researcher specializing in multi-agent systems, Bayesian optimization, and robotic decision-making under uncertainty. His work sits at the intersection of machine learning and robotics, developing algorithms that enable intelligent, coordinated behavior among autonomous agents. Zhang's most impactful contribution is his work on Gaussian Max-Value Entropy Search for multi-agent Bayesian optimization (2023, 10 citations), which extends entropy search methods to collaborative settings where multiple agents efficiently explore black-box functions — a critical challenge in real-world optimization tasks. Complementing this, his research on multi-armed bandit learning on graphs (2023, 6 citations) addresses sequential decision-making under physical constraints, a problem directly relevant to robotic navigation and resource allocation. His 2021 work on dynamic source location estimation (7 citations) demonstrates his interest in practical multi-robot coordination, designing sensor-driven algorithms that guide robot swarms toward unknown sources — with applications ranging from environmental monitoring to search-and-rescue operations. Additional contributions to cloud manufacturing task allocation highlight his broader interest in intelligent system design. Though early in his career, Zhang's research reveals a coherent vision: building theoretically grounded, sample-efficient algorithms that scale to real-world multi-agent scenarios, making him a researcher worth following in autonomous systems and sequential decision-making.