Selected Papers: 'Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling' (IJCAI 2025), 'A Meta-Game Evaluation Framework for Deep Multiagent Reinforcement Learning' (IJCAI 2024, Best Paper Award of ALA Workshop at AAMAS 2024), 'Evolution Strategies for Approximate Solution of Bayesian Games' (AAAI 2021), 'Structure Learning for Approximate Solution of Many-Player Games' (AAAI 2020).
Research Experience
Research Engineer at Google DeepMind, New York, Feb. 2024-Now; Research Scientist Intern at DeepMind Alberta, Edmonton, Jun. 2022-Nov. 2022; Software Engineering Intern at Google Inc., Core Google Display Ad Team, Remote, Jun. 2021-Aug. 2021.
Education
Ph.D. in Computer Science and Engineering from the University of Michigan, U.S., from Sep. 2018 to Jan. 2024, under the supervision of Prof. Michael P. Wellman; B.S.E. in Computer Science (IEEE Honored Class) from Shanghai Jiao Tong University, China, from Sep. 2014 to Jun. 2018.
Background
Aspires to study intelligence through a multi-agent lens, working on computational game theory, (deep) multi-agent planning/learning, agent-based simulation methods, auctions, and data markets.