Advances in reinforcement learning for traffic signal control: a review of recent progress
Intelligent Transportation Infrastructure · 29.01.2025 · 4
DOI: 10.1093/iti/liaf009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligent Transportation Infrastructure, online erschienen am 05.05.2024. Verfasst von Feng Xiao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 185 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan, Central Guidance for Local Science and Technology Development Fund Projects.
Abstract (Originalsprache)
In recent years, reinforcement learning (RL) methods have shown substantial promise in traffic signal control (TSC), drawing significant attention from academia and industry. The integration of RL with advanced machine learning methods offers a novel approach to tackling dynamic and complex traffic conditions. Previous reviews have primarily focused on foundational RL methods or controlled experimental setups, with limited attention to advanced methodologies and real-world complexities. To address this gap, this paper provides a comprehensive review of recent advancements in RL-based TSC from both methodological and application perspectives. From the methodological perspective, it comprehensively examines how advanced RL methods are integrated with state-of-the-art artificial intelligence algorithms to address TSC challenges. From the application perspective, it systematically reviews studies that extend RL approaches to more complex and multi-modal traffic scenarios. Furthermore, it identifies critical challenges, including model scalability, real-time adaptability, the sim-to-real gap, and the integration of TSC with broader urban transport systems, offering insights, and directions for future research.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Sichuan
- Central Guidance for Local Science and Technology Development Fund Projects
Zitieren
APA
Xiao, F., Lu, J., Li, L., Tu, W., & Li, C. (2025). Advances in reinforcement learning for traffic signal control: a review of recent progress. Intelligent Transportation Infrastructure, 4. https://doi.org/10.1093/iti/liaf009
Vancouver
Xiao F, Lu J, Li L, Tu W, Li C. Advances in reinforcement learning for traffic signal control: a review of recent progress. Intelligent Transportation Infrastructure. 2025;4. doi:10.1093/iti/liaf009
BibTeX
@article{Xiao2025,
author = {Xiao, Feng and Lu, Jiaming and Li, Lu and Tu, Wenwen and Li, Chaojing},
title = {Advances in reinforcement learning for traffic signal control: a review of recent progress},
journal = {Intelligent Transportation Infrastructure},
year = {2025},
volume = {4},
doi = {10.1093/iti/liaf009}
}
EUVIMED