Zaiwei Chen

Zaiwei Chen is an Assistant Professor in the Edwardson School of Industrial Engineering at Purdue University. His research focuses on developing theoretical foundations for sequential decision-making under uncertainty, particularly in reinforcement learning, multi-agent systems, and optimization. He leads projects on data-efficient algorithms with applications in control and game theory.

He holds a Ph.D. in Machine Learning and dual M.S. degrees in Mathematics and Operations Research from Georgia Institute of Technology, and a B.S. in Electrical Engineering from Zhejiang University.

His research bridges applied probability, machine learning, and optimization to create robust algorithms for complex systems. Recent work emphasizes convergence guarantees in multi-agent reinforcement learning and scalable solutions for high-dimensional problems.

Chen's publications demonstrate a consistent focus on theoretical guarantees for reinforcement learning algorithms, particularly in stochastic and game-theoretic settings. Key trends include Lyapunov stability frameworks, finite-sample analysis, and methods to overcome computational bottlenecks like the "curse of dimensionality."

Awards include:

• Solberg Academic Excellence Scholarship
• PIMCO Postdoctoral Fellowship in Data Science (2022)
• Sigma Xi Best Ph.D. Thesis Award
• Runner-up for SIGMETRICS Doctoral Dissertation Award

He actively recruits PhD students to work on reinforcement learning theory and maintains collaborations with Caltech and Georgia Tech. Future work includes scalable multi-agent learning frameworks and real-world applications in industrial systems.