Seminar: Reinforcement Learning for Traffic Signal Control


Department of Systems Engineering and Engineering Management

The Chinese University of Hong Kong

Title: Reinforcement Learning for Traffic Signal Control

Speaker: Zhenhui (Jessie) Li, Pennsylvania State University

Abstract: Large-scale mobility data can be collected from mobile phones, car navigation systems, road surveillance cameras, and loop sensors. Turning such raw data into knowledge can provide insights about our city and empower the city to be more intelligent. 

In this talk, I will focus on data-driven traffic signal control. I will discuss our recent research work on deep reinforcement learning model for traffic signal control. We also plan to conduct field experiments in Hangzhou China for traffic signal control. I would like to share my insights and experiences learnt from addressing real-world traffic problem. 

Biography: Dr. Zhenhui (Jessie) Li is a tenured associate professor of Information Sciences and Technology at the Pennsylvania State University. She is Haile family early career endowed professor. Prior to joining Penn State, she received her PhD degree in Computer Science from University of Illinois Urbana-Champaign in 2012, where she was a member of data mining research group. Her research has been focused on mining spatial-temporal data with applications in transportation, ecology, environment, social science, and urban computing. She is a passionate interdisciplinary researcher and has been actively collaborating with cross-domain researchers. She has served as organizing committee or senior program committee of many conferences including KDD, ICDM, SDM, CIKM, and SIGSPATIAL. She has received NSF CAREER award, junior faculty excellence in research, and George J. McMurtry junior faculty excellence in teaching and learning award. She is currently taking sabbatical leave (2018-2019) at Hangzhou to conduct city brain research. She is looking for interns to join her research team in Hangzhou. To learn more, please visit her homepage:

Thursday, September 27, 2018 - 16:30 to 17:30