Shengbo Wang
Assistant Professor of Industrial and Systems Engineering
Biography
Dr. 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 span a broad spectrum within applied probability, including stochastic modeling, reinforcement learning, distributionally robust control, and simulation methods for machine learning. He focuses on developing tractable probabilistic models and designing algorithms for data-driven dynamic decision-making under uncertainty, specifically addressing reliability and scalability challenges in modern managerial and engineering applications.Research Summary
I am interested in a wide range of research areas within applied probability, stochastic modeling, and simulation. My work focuses on the design and analysis of algorithms tailored for the learning and control of dynamic engineering systems, with applications in management science and operations research, addressing the reliability and scalability challenges that emerge from contemporary problems. Key areas of my research include:- Design, analyze, and implement sample-efficient estimators capable of learning key system characteristics.
- Achieve efficient reinfocement learning (RL) and control of stable stochastic systems.
- Develop statistically tractable, data-driven modeling paradigms and algorithms for robust dynamic policy learning and RL, leveraging distributionally robust optimization.
- Advance deep learning techniques in policy learning through the development of computationally efficient estimation procedures using applied probabilistic tools.
Appointments
- Daniel J. Epstein Department of Industrial and Systems Engineering
- Shengbo Wang has not listed an office location.
- shengbow@usc.edu