Optimizing Traffic Signal Control Using Deep Reinforcement Learning: A Case Study of Hangzhou

DOI

10.2991/978-94-6239-721-7_2How to use a DOI?

Keywords

DRL; Traffic Control; Single Intersection Optimization; Traffic Jam; Multimodal Data Fusion

Abstract

Urban development faces the problem of traffic congestion as one of its major challenges. The conventional approaches to signal control work well in the context of optimization at a single point but do not scale well to large road networks or more complicated environments in which dynamics occur. Recently, Deep Reinforcement Learning (DRL) has proven useful in optimizing traffic signals where it can optimize both adaptively and globally due to the interactive learning process. The paper discusses the evolution of DRL in traffic signal control research, starting with single intersections and extending to multi-agent cooperation, and provides an insight into the Hangzhou intelligent traffic case study. It is found that this method can be highly efficient in terms of reducing the average delay and increasing the road network efficiency, however, there are still practical limitations, including data noise, multi-source uncertainty, and lack of robustness. The further research directions will focus on integrating multimodal data, improving robust modeling, and so on to make intelligent transportation be applied to real road instead of remaining in the theory.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Anran Li
PY  - 2026
DA  - 2026/07/06
TI  - Optimizing Traffic Signal Control Using Deep Reinforcement Learning: A Case Study of Hangzhou
BT  - Proceedings of the 2026 6th International Conference on Public Management and Intelligent Society (PMIS 2026)
PB  - Atlantis Press
SP  - 4
EP  - 12
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-721-7_2
DO  - 10.2991/978-94-6239-721-7_2
ID  - Li2026
ER  -