2026-06-09T02:17:00Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/70022024-05-20T08:02:46Zcom_10259.4_104com_10259_2604col_10259_6848

Reinforcement learning for Traffic Signal Control: Comparison with commercial systems Cabrejas Egea, Álvaro Zhang, Raymond Walton, Neil Tráfico Infraestructuras Traffic Infrastructures Ingeniería civil Transportes Tecnología Civil engineering Transportation Technology Trabajo presentado en: R-Evolucionando el transporte, XIV Congreso de Ingeniería del Transporte (CIT 2021), realizado en modalidad online los días 6, 7 y 8 de julio de 2021, organizado por la Universidad de Burgos In recent years, Intelligent Transportation Systems are leveraging the power of increased sensory coverage and available computing power to deliver data-intensive solutions achieving higher levels of performance than traditional systems. Within Traffic Signal Control (TSC), this has allowed the emergence of Machine Learning (ML) based systems. Among this group, Reinforcement Learning (RL) approaches have performed particularly well. Given the lack of industry standards in ML for TSC, literature exploring RL often lacks comparison against commercially available systems and straightforward formulations of how the agents operate. Here we attempt to bridge that gap. We propose three different architectures for RL based agents and compare them against currently used commercial systems MOVA, SurTrac and Cyclic controllers and provide pseudo-code for them. The agents use variations of Deep Q-Learning (Double Q Learning, Duelling Architectures and Prioritised Experience Replay) and Actor Critic agents, using states and rewards based on queue length measurements. Their performance is compared in across different map scenarios with variable demand, assessing them in terms of the global delay generated by all vehicles. We find that the RL-based systems can significantly and consistently achieve lower delays when compared with traditional and existing commercial systems. This work was part funded by EPSRC Grant EP/L015374 and part funded by The Alan Turing Institute and the Toyota Mobility Foundation. The authors thank Dr. W. Chernicoff for the initial discussions and drive that made this project possible. 2022-09-22T06:41:43Z 2022-09-22T06:41:43Z 2021-07 info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion 978-84-18465-12-3 http://hdl.handle.net/10259/7002 10.36443/10259/7002 eng R-Evolucionando el transporte http://hdl.handle.net/10259/6490 https://doi.org/10.36443/9788418465123 info:eu-repo/grantAgreement/EPSRC//EP%2FL015374 info:eu-repo/semantics/openAccess application/pdf Universidad de Burgos. Servicio de Publicaciones e Imagen Institucional https://riubu.ubu.es/bitstream/10259/7002/3/Cabrejas_CIT2021_2673-2692.pdf.jpg Hispana TEXT http://rightsstatements.org/vocab/CNE/1.0/ RIUBU. Repositorio Institucional de la Universidad de Burgos http://hdl.handle.net/10259/7002