Holds a patent related to information design in multi-agent reinforcement learning.
Research Experience
Has research experience in multi-agent reinforcement learning, game theory with a focus on information design, and using LLMs for game solvers.
Education
Currently a Ph.D. student (data science program) at the School of Data Science, The Chinese University of Hong Kong, Shenzhen, advised by Prof. Baoxiang Wang and Prof. Hongyuan Zha. Also a joint Ph.D. student at the Shenzhen Loop Area Institute.
Background
Research interests include designing efficient algorithms to guide agents toward better equilibriums in multi-agent tasks; solving sequential social dilemmas, by designing learning algorithms that incorporate mechanism design; and designing learning methods for mechanism design problems. Focuses mainly on sequential mixed-motive multi-agent scenarios, with a particular interest in communication mechanisms (such as information design, Bayesian persuasion, cheap talk) and other mechanisms that influence others, such as incentivization. Expertise lies in reinforcement learning, particularly multi-agent hyper-gradient modeling, and large language models (LLMs).
Miscellany
Personal interests include reading literature, such as 'Perfume: The Story of a Murderer'.