Dr. Shengbo Wang

Biography

Shengbo Wang is an Assistant Professor in the Daniel J. Epstein Department of Industrial and Systems Engineering at the University of Southern California. He received his Ph.D. in Management Science and Engineering from Stanford University, where he was co-advised by Professors Peter Glynn and Jose Blanchet. His research interests encompass a broad spectrum of applied probability, stochastic modeling, and reinforcement learning, with a focus on developing tractable probabilistic models and algorithms for data-driven dynamic decision-making under uncertainty. His work addresses reliability and scalability challenges in modern managerial engineering applications. Key areas of his research include the design and analysis of algorithms engineered for learning and controlling dynamic engineering systems, particularly within the domains of management science and operations research. He aims to achieve efficient reinforcement learning control in stable stochastic systems and advance models that leverage distributionally robust optimization to enhance dynamic policy learning. Additionally, he applies deep learning techniques to improve policy learning and develops computationally efficient estimation procedures using applied probabilistic tools.

Research Interests

Awards