His research focuses on bridging operations research and reinforcement learning to support data-driven decision-making in complex systems.
Online decision-making in multiagent systems is a fundamental and complex problem that arises in various applications in new mobility ecosystem (e.g., matching, incentives) and supply chain management (sourcing, pricing). Leveraging and integrating the state-of-the-art knowledge in reinforcement learning, mechanism design, and online algorithms can push the boundaries of each field and solve the unsolved problems in real-world applications.
He worked in Argonne National Laboratory before pursuing his Ph.D. degree. His recent graduate studies are supported by National Science Foundation CMMI, the Michigan Institute for Data Science, Mcity (U-M connected & automated vehicle research center), and Ford alliance research.
I am honored to be advised by:
Dr. Romesh Saigal. Professor, Industrial and Operations Engineering, University of Michigan.
Dr. Robert C. Hampshire. Associate Professor, Gerald R. Ford School of Public Policy, the Michigan Institute for Data Science, and Transportation Research Institute’s (UMTRI), University of Michigan.
Qi Luo will be on the academic job market in 2020.
Qi’s joint work with Zhiyuan Huang and Prof. Henry Lam titled “Dynamic Congestion Pricing for Ridesourcing Traffic: A Simulation-Based Approach.” won the Winter Simulation Conference I-Sim Ph.D. Colloquium Best Student Paper Award in 2019.
Hao Yuan’s work co-authored with Qi Luo and Prof. Cong Shi titled “Marrying Stochastic Gradient Descent with Bandits: Learning Algorithms for Inventory Systems with Fixed Costs.” won the 2019 Applied Probability Society Student paper competition, finalist and the Murty Prize for best paper on optimization.