Traffic flow management based on reinforcement learning

Traffic jams often occur due to inefficient control of traffic lights at intersections, that is, due to the fact that their settings are not sufficiently adapted to specific conditions. Currently, foreign research is actively underway in the field of applying machine learning methods with reinforcement to optimize traffic flows at intersections, which once again shows the urgency of the problem. The prospect of using reinforcement learning lies in the ability to control the dynamics of complex processes without human intervention. To maintain the efficiency and safety of moving cars in urban environments, there are systems that control traffic flows using traffic lights. The paper considers the existing types of traffic flow management systems. The analysis revealed their positive and negative qualities. The article proposes an intelligent control system based on the principles of reinforcement learning, supplemented by an approximator using a neural network. The network architecture is a multi-layered perceptron, with two hidden layers with ReLU activation functions. The process of agent training and the results of control system modeling in the SUMO microscopic modeling environment are presented. The results are presented in the form of a graph of the dynamics of agent training, heat maps of intersections when simulating rush hour traffic and in case of an accident before and after exposure. The proposed system makes it possible to increase the traffic intensity in the intersection network by 40% and 25% during rush hour and traffic accidents, respectively. In addition, the future prospects of its development are reflected.

1. Raeisi M., Mahboob A.S. Intelligent Control of Urban Intersection Traffic Light Based on Reinforcement Learning Algorithm. In: 2021 26th International Computer Conference, Computer Society of Iran (CSICC), 03–04 March 2021, Tehran, Iran. IEEE; 2021. P. 1–5. https://doi.org/10.1109/CSICC52343.2021.9420622

2. Zhou M., Yu Y., Qu X. Development of an Efficient Driving Strategy for Connected and Automated Vehicles at Signalized Intersections: A Reinforcement Learning Approach. IEEE Transactions on Intelligent Transportation Systems. 2020;21(1):433–443. https://doi.org/10.1109/TITS.2019.2942014

3. Ducrocq R., Farhi N. Deep Reinforcement Q-Learning for Intelligent Traffic Signal Control with Partial Detection. International Journal of Intelligent Transportation Systems Research. 2023;21(1):192–206. https://doi.org/10.1007/s13177-023-00346-4

4. Farazi N.P., Ahamed T., Barua L., Zou B. Deep Reinforcement Learning and Transportation Research: A Comprehensive Review. arXiv. URL: https://doi.org/10.48550/arXiv.2010.06187 [Accessed 31st October 2025].

5. Qadri S.Sh.S.M., Gökçe M.A., Öner E. State-of-art review of traffic signal control methods: challenges and opportunities. European Transport Research Review. 2020;12(1). https://doi.org/10.1186/s12544-020-00439-1

6. Rutkovsky V.N., Kapski D.V. Analysis, development and implementation of adaptive algorithms for (flexible) traffic light regulations. System analysis and applied information science. 2023;(3):4–16. (In Russ.). https://doi.org/10.21122/2309-4923-2023-3-4-16

7. Agafonov A.A., Efimenko E.Yu. Comparison of algorithms for controlling traffic light signals in a large-scale scenario for modeling vehicle movement. In: Information Technologies and Nanotechnologies (ITNT-2022): Proceedings of the VIII International Conference and Youth School: Volume 3, 23–27 May 2022, Samara, Russia. Samara: Samara National Research University; 2022. P. 031382. (In Russ.).

8. Agafonov A.A., Yumaganov A.S., Myasnikov V.V. Adaptive traffic signal control based on neural network prediction of weighted traffic flow. Optoelectronics, Instrumentation and Data Processing. 2022;58(5):503–513. https://doi.org/10.3103/s8756699022050016

9. Dake D.K., Gadze J.D., Klogo G.S., Nunoo-Mensah H. Traffic Engineering in Software-defined Networks using Reinforcement Learning: A Review. International Journal of Advanced Computer Science and Applications. 2021;12(5):330–345.

10. Fadila J.N., Wahab N.H.A., Alshammari A., et al. Comprehensive review of smart urban traffic management in the context of the fourth industrial revolution. IEEE Access. 2024;12:196866–196886. https://doi.org/10.1109/access.2024.3509572

11. Liang X., Du X., Wang G., Han Zh. A Deep Reinforcement Learning Network for Traffic Light Cycle Control. IEEE Transactions on Vehicular Technology. 2019;68(2):1243–1253. https://doi.org/10.1109/TVT.2018.2890726

12. Kunjir M., Chawla S. Offline Reinforcement Learning for Road Traffic Control. arXiv. URL: https://doi.org/10.48550/arXiv.2201.02381 [Accessed 20th October 2025].

13. Tan K.L., Sharma A., Sarkar S. Robust Deep Reinforcement Learning for Traffic Signal Control. Journal of Big Data Analytics in Transportation. 2020;2(3):263–274. https://doi.org/10.1007/s42421-020-00029-6

14. Orlova E.V. Reinforcement learning as an artificial intelligence technology to solve socio-economic problems: algorithms performance assessment. п-Economy. 2023;16(5):38–50. (In Russ.). https://doi.org/10.18721/JE.16503

15. Saadi A., Abghour N., Chiba Z., Moussaid Kh., Ali S. A survey of reinforcement and deep reinforcement learning for coordination in intelligent traffic light control. Journal of Big Data. 2025;12(1). https://doi.org/10.1186/s40537-025-01104-x

16. Korchagin A.P. Hybrid agent training system using A2C and evolutionary strategies. Modeling, Optimization and Information Technology. 2025;13(3). (In Russ.). https://doi.org/10.26102/2310-6018/2025.50.3.029