{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T12:36:04Z","timestamp":1776602164771,"version":"3.51.2"},"reference-count":96,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"DOI":"10.1186\/s40537-025-01104-x","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T13:14:39Z","timestamp":1744031679000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["A survey of reinforcement and deep reinforcement learning for coordination in intelligent traffic light control"],"prefix":"10.1186","volume":"12","author":[{"given":"Aicha","family":"Saadi","sequence":"first","affiliation":[]},{"given":"Noureddine","family":"Abghour","sequence":"additional","affiliation":[]},{"given":"Zouhair","family":"Chiba","sequence":"additional","affiliation":[]},{"given":"Khalid","family":"Moussaid","sequence":"additional","affiliation":[]},{"given":"Saadi","family":"Ali","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,7]]},"reference":[{"key":"1104_CR1","unstructured":"Casas N. Deep deterministic policy gradient for urban traffic light control. arXiv preprint arXiv:1703.09035. 2017."},{"key":"1104_CR2","unstructured":"Gao J, Shen Y, Liu J, Ito M, Shiratori N. Adaptive traffic signal control: deep reinforcement learning algorithm with experience replay and target network. arXiv preprint arXiv:1705.02755. 2017."},{"key":"1104_CR3","unstructured":"Schrank D, Eisele B, Lomax T, Bak J. 2015 urban mobility scorecard. 2015."},{"issue":"2","key":"1104_CR4","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/TVT.2018.2890726","volume":"68","author":"X Liang","year":"2019","unstructured":"Liang X, Du X, Wang G, Han Z. A deep reinforcement learning network for traffic light cycle control. IEEE Trans Veh Technol. 2019;68(2):1243\u201353.","journal-title":"IEEE Trans Veh Technol"},{"issue":"2","key":"1104_CR5","first-page":"653","volume":"16","author":"A Abadi","year":"2014","unstructured":"Abadi A, Rajabioun T, Ioannou PA. Traffic flow prediction for road transportation networks with limited traffic data. IEEE Trans Intell Transport Syst. 2014;16(2):653\u201362.","journal-title":"IEEE Trans Intell Transport Syst"},{"key":"1104_CR6","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-642-11688-9_18","volume-title":"Interactive collaborative information systems","author":"B Bakker","year":"2010","unstructured":"Bakker B, Whiteson S, Kester L, Groen FC. Traffic light control by multiagent reinforcement learning systems. In: Babu\u0161ka R, Groen FC, editors. Interactive collaborative information systems. Berlin, Heidelberg: Springer Berlin Heidelberg; 2010. p. 475\u2013510. https:\/\/doi.org\/10.1007\/978-3-642-11688-9_18."},{"issue":"5","key":"1104_CR7","doi-asserted-by":"publisher","first-page":"2373","DOI":"10.3390\/s23052373","volume":"23","author":"A Mushtaq","year":"2023","unstructured":"Mushtaq A, Haq IU, Sarwar MA, Khan A, Khalil W, Mughal MA. Multi-agent reinforcement learning for traffic flow management of autonomous vehicles. Sensors. 2023;23(5):2373.","journal-title":"Sensors"},{"key":"1104_CR8","unstructured":"Shahsavari B, Abbeel P. Short-term traffic forecasting: modeling and learning spatio-temporal relations in transportation networks using graph neural networks. University of California at Berkeley, Technical Report No. UCB\/EECS(2015). 2015-243."},{"issue":"1","key":"1104_CR9","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TITS.2020.3008612","volume":"23","author":"A Haydari","year":"2020","unstructured":"Haydari A, Y\u0131lmaz Y. Deep reinforcement learning for intelligent transportation systems: a survey. IEEE Trans Intell Transp Syst. 2020;23(1):11\u201332.","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1104_CR10","doi-asserted-by":"publisher","unstructured":"Lillicrap TP. Continuous control with deep reinforcement learning. arXiv reprint. arXiv:1509.02971. 2015. https:\/\/doi.org\/10.48550\/arXiv.1509.02971.","DOI":"10.48550\/arXiv.1509.02971"},{"key":"1104_CR11","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.cirpj.2022.11.003","volume":"40","author":"C Li","year":"2023","unstructured":"Li C, Zheng P, Yin Y, Wang B, Wang L. Deep reinforcement learning in smart manufacturing: a review and prospects. CIRP J Manuf Sci Technol. 2023;40:75\u2013101.","journal-title":"CIRP J Manuf Sci Technol"},{"key":"1104_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036","volume":"269","author":"Z Wang","year":"2020","unstructured":"Wang Z, Hong T. Reinforcement learning for building controls: the opportunities and challenges. Appl Energy. 2020;269: 115036.","journal-title":"Appl Energy"},{"issue":"2","key":"1104_CR13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/3447556.3447565","volume":"22","author":"H Wei","year":"2021","unstructured":"Wei H, Zheng G, Gayah V, Li Z. Recent advances in reinforcement learning for traffic signal control: a survey of models and evaluation. ACM SIGKDD Explor Newsl. 2021;22(2):12\u20138.","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"1104_CR14","unstructured":"Steingrover M, Schouten R, Peelen S, Nijhuis E, Bakker B. Reinforcement learning of traffic light controllers adapting to traffic congestion. In BNAIC; 2005. pp. 216\u2013223."},{"key":"1104_CR15","doi-asserted-by":"crossref","unstructured":"Arabnejad H, Pahl C, Jamshidi P, Estrada G. A comparison of reinforcement learning techniques for fuzzy cloud auto-scaling. In 2017 17th IEEE\/ACM international symposium on cluster, cloud and grid computing (CCGRID). IEEE; 2017, pp. 64\u201373.","DOI":"10.1109\/CCGRID.2017.15"},{"issue":"5","key":"1104_CR16","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1016\/j.tics.2019.02.006","volume":"23","author":"M Botvinick","year":"2019","unstructured":"Botvinick M, Ritter S, Wang JX, Kurth-Nelson Z, Blundell C, Hassabis D. Reinforcement learning, fast and slow. Trends Cogn Sci. 2019;23(5):408\u201322.","journal-title":"Trends Cogn Sci"},{"key":"1104_CR17","doi-asserted-by":"publisher","first-page":"15","DOI":"10.52825\/scp.v3i.116","volume":"3","author":"C Louw","year":"2022","unstructured":"Louw C, Labuschagne L, Woodley T. A comparison of reinforcement learning agents applied to traffic signal optimisation. SUMO Conf Proc. 2022;3:15\u201343.","journal-title":"SUMO Conf Proc"},{"key":"1104_CR18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694","author":"P Henderson","year":"2018","unstructured":"Henderson P, Islam R, Bachman P, Pineau J, Precup D, Meger D. Deep reinforcement learning that matters. Proc AAAI Conf Artif Intell. 2018. https:\/\/doi.org\/10.1609\/aaai.v32i1.11694.","journal-title":"Proc AAAI Conf Artif Intell."},{"issue":"9","key":"1104_CR19","doi-asserted-by":"publisher","first-page":"2419","DOI":"10.1007\/s10994-021-05961-4","volume":"110","author":"G Dulac-Arnold","year":"2021","unstructured":"Dulac-Arnold G, Levine N, Mankowitz DJ, Li J, Paduraru C, Gowal S, Hester T. Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. Mach Learn. 2021;110(9):2419\u201368.","journal-title":"Mach Learn"},{"issue":"19","key":"1104_CR20","doi-asserted-by":"publisher","first-page":"12185","DOI":"10.3390\/su141912185","volume":"14","author":"A Rehman","year":"2022","unstructured":"Rehman A, Saba T, Haseeb K, Alam T, Lloret J. Sustainability model for the internet of health things (IoHT) using reinforcement learning with mobile edge secured services. Sustainability. 2022;14(19):12185.","journal-title":"Sustainability"},{"issue":"1","key":"1104_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.13164\/mendel.2021.1.001","volume":"27","author":"R Parak","year":"2021","unstructured":"Parak R, Matousek R. Comparison of multiple reinforcement learning and deep reinforcement learning methods for the task aimed at achieving the goal. MENDEL J. 2021;27(1):1\u20138.","journal-title":"MENDEL J"},{"key":"1104_CR22","doi-asserted-by":"publisher","first-page":"99155","DOI":"10.1109\/ACCESS.2021.3096666","volume":"9","author":"DF Borges","year":"2021","unstructured":"Borges DF, Leite JPR, Moreira EM, Carpinteiro OA. Traffic light control using hierarchical reinforcement learning and options framework. IEEE Access. 2021;9:99155\u201365.","journal-title":"IEEE Access"},{"key":"1104_CR23","unstructured":"Tokarchuk L, Bigham J, Cuthbert L. Fuzzy sarsa: an approach to fuzzifying sarsa learning. In Proceedings of the International Conference on Computational Intelligence for Modeling, Control and Automation. 2004."},{"key":"1104_CR24","doi-asserted-by":"crossref","unstructured":"Arvind CS, Senthilnath J. Autonomous RL: autonomous vehicle obstacle avoidance in a dynamic environment using MLP-SARSA reinforcement learning. In 2019 IEEE 5th International Conference on Mechatronics System and Robots (ICMSR). IEEE; 2019, pp. 120\u2013124.","DOI":"10.1109\/ICMSR.2019.8835462"},{"key":"1104_CR25","doi-asserted-by":"publisher","first-page":"54074","DOI":"10.1109\/ACCESS.2020.2981434","volume":"8","author":"T Alfakih","year":"2020","unstructured":"Alfakih T, Hassan MM, Gumaei A, Savaglio C, Fortino G. Task offloading and resource allocation for mobile edge computing by deep reinforcement learning based on SARSA. IEEE Access. 2020;8:54074\u201384.","journal-title":"IEEE Access"},{"issue":"3","key":"1104_CR26","doi-asserted-by":"publisher","first-page":"2800","DOI":"10.1007\/s11227-020-03364-1","volume":"77","author":"A Asghari","year":"2021","unstructured":"Asghari A, Sohrabi MK, Yaghmaee F. Task scheduling, resource provisioning, and load balancing on scientific workflows using parallel SARSA reinforcement learning agents and genetic algorithm. J Supercomput. 2021;77(3):2800\u201328.","journal-title":"J Supercomput"},{"issue":"6","key":"1104_CR27","doi-asserted-by":"publisher","first-page":"4010","DOI":"10.3390\/app13064010","volume":"13","author":"H Wang","year":"2023","unstructured":"Wang H, Zhu J, Gu B. Model-based deep reinforcement learning with traffic inference for traffic signal control. Appl Sci. 2023;13(6):4010.","journal-title":"Appl Sci"},{"issue":"11","key":"1104_CR28","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","volume":"25","author":"MP McBee","year":"2018","unstructured":"McBee MP, Awan OA, Colucci AT, Ghobadi CW, Kadom N, Kansagra AP, et al. Deep learning in radiology. Acad Radiol. 2018;25(11):1472\u201380.","journal-title":"Acad Radiol"},{"key":"1104_CR29","doi-asserted-by":"crossref","unstructured":"Garg D, Chli M, Vogiatzis G. Deep reinforcement learning for autonomous traffic light control. In 2018 3rd IEEE international conference on intelligent transportation engineering (ICITE). IEEE; 2018, pp. 214\u2013218.","DOI":"10.1109\/ICITE.2018.8492537"},{"key":"1104_CR30","unstructured":"Li Y. Deep reinforcement learning: an overview. arXiv preprint arXiv. 2017;1701.07274."},{"key":"1104_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","volume":"8","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Farhan L. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021;8:1\u201374.","journal-title":"J Big Data"},{"issue":"1","key":"1104_CR32","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1186\/s40537-023-00838-w","volume":"10","author":"S \u00d6zg\u00fcr","year":"2023","unstructured":"\u00d6zg\u00fcr S, Orman M. Application of deep learning technique in next generation sequence experiments. J Big Data. 2023;10(1):160.","journal-title":"J Big Data"},{"key":"1104_CR33","unstructured":"Schutera M, Goby N, Smolarek S, Reischl M. Distributed traffic light control at uncoupled intersections with real-world topology by deep reinforcement learning. arXiv preprint arXiv:. 2018. 1811.11233."},{"issue":"1","key":"1104_CR34","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s43067-023-00081-6","volume":"10","author":"SA Sayed","year":"2023","unstructured":"Sayed SA, Abdel-Hamid Y, Hefny HA. Artificial intelligence-based traffic flow prediction: a comprehensive review. J Electric Syst Inf Technol. 2023;10(1):13.","journal-title":"J Electric Syst Inf Technol"},{"key":"1104_CR35","unstructured":"Kanis S, Samson L, Bloembergen D, Bakker T. Back to basics: deep reinforcement learning in traffic signal control. arXiv preprint arXiv. (2021),2109.07180."},{"issue":"3","key":"1104_CR36","doi-asserted-by":"publisher","first-page":"362","DOI":"10.17775\/CSEEJPES.2018.00520","volume":"4","author":"D Zhang","year":"2018","unstructured":"Zhang D, Han X, Deng C. Review on the research and practice of deep learning and reinforcement learning in smart grids. CSEE J Power Energy Syst. 2018;4(3):362\u201370.","journal-title":"CSEE J Power Energy Syst"},{"key":"1104_CR37","doi-asserted-by":"crossref","unstructured":"Tiong T, Saad I, Teo KTK, Bin Lago H. Deep reinforcement learning with robust deep deterministic policy gradient. In 2020 2nd International Conference on Electrical, Control and Instrumentation Engineering (ICECIE). IEEE; 2020, pp. 1\u20135.","DOI":"10.1109\/ICECIE50279.2020.9309539"},{"issue":"2","key":"1104_CR38","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.1109\/TVT.2019.2962514","volume":"69","author":"J Lee","year":"2019","unstructured":"Lee J, Chung J, Sohn K. Reinforcement learning for joint control of traffic signals in a transportation network. IEEE Trans Veh Technol. 2019;69(2):1375\u201387.","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"1104_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/15472450.2018.1527694","volume":"24","author":"M Xu","year":"2020","unstructured":"Xu M, Wu J, Huang L, Zhou R, Wang T, Hu D. Network-wide traffic signal control based on the discovery of critical nodes and deep reinforcement learning. J Intell Transport Syst. 2020;24(1):1\u201310.","journal-title":"J Intell Transport Syst"},{"key":"1104_CR40","unstructured":"Hausknecht, M., & Stone, P. Deep reinforcement learning in parameterized action space. arXiv preprint arXiv: (2015),1511.04143."},{"issue":"3-4","key":"1104_CR41","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Fran\u00e7ois-Lavet","year":"2018","unstructured":"Fran\u00e7ois-Lavet V, Henderson P, Islam R, Bellemare MG, Pineau J. An introduction to deep reinforcement learning. Found Trends\u00ae Mach Learn. 2018;11(3\u20134):219\u2013354. https:\/\/doi.org\/10.1561\/2200000071.","journal-title":"Found Trends\u00ae Mach Learn"},{"key":"1104_CR42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295","author":"H Van Hasselt","year":"2016","unstructured":"Van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double q-learning. Proc AAAI Conf Artif Intell. 2016. https:\/\/doi.org\/10.1609\/aaai.v30i1.10295.","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"9","key":"1104_CR43","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1049\/iet-its.2018.5170","volume":"12","author":"CH Wan","year":"2018","unstructured":"Wan CH, Hwang MC. Value-based deep reinforcement learning for adaptive isolated intersection signal control. IET Intell Transport Syst. 2018;12(9):1005\u201310.","journal-title":"IET Intell Transport Syst"},{"issue":"11","key":"1104_CR44","doi-asserted-by":"publisher","first-page":"8315","DOI":"10.1109\/JIOT.2022.3155667","volume":"9","author":"J Liu","year":"2022","unstructured":"Liu J, Ahmed M, Mirza MA, Khan WU, Xu D, Li J, et al. RL\/DRL meets vehicular task offloading using edge and vehicular cloudlet: a survey. IEEE Internet Things J. 2022;9(11):8315\u201338.","journal-title":"IEEE Internet Things J"},{"issue":"6","key":"1104_CR45","doi-asserted-by":"publisher","first-page":"6768","DOI":"10.11591\/ijece.v12i6.pp6768-6776","volume":"12","author":"H Alturkistani","year":"2022","unstructured":"Alturkistani H, El-Affendi MA. Optimizing cybersecurity incident response decisions using deep reinforcement learning. Int J Electric Comput Eng. 2022;12(6):6768.","journal-title":"Int J Electric Comput Eng"},{"issue":"8","key":"1104_CR46","doi-asserted-by":"publisher","first-page":"2834","DOI":"10.3390\/en15082834","volume":"15","author":"D Lee","year":"2022","unstructured":"Lee D, Koo S, Jang I, Kim J. Comparison of deep reinforcement learning and PID controllers for automatic cold shutdown operation. Energies. 2022;15(8):2834.","journal-title":"Energies"},{"issue":"8","key":"1104_CR47","doi-asserted-by":"publisher","first-page":"4919","DOI":"10.1109\/TITS.2020.2984033","volume":"22","author":"N Kumar","year":"2020","unstructured":"Kumar N, Rahman SS, Dhakad N. Fuzzy inference enabled deep reinforcement learning-based traffic light control for intelligent transportation system. IEEE Trans Intell Transp Syst. 2020;22(8):4919\u201328.","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"8","key":"1104_CR48","doi-asserted-by":"publisher","first-page":"8243","DOI":"10.1109\/TVT.2020.2997896","volume":"69","author":"T Wu","year":"2020","unstructured":"Wu T, Zhou P, Liu K, Yuan Y, Wang X, Huang H, Wu DO. Multi-agent deep reinforcement learning for urban traffic light control in vehicular networks. IEEE Trans Veh Technol. 2020;69(8):8243\u201356.","journal-title":"IEEE Trans Veh Technol"},{"issue":"6","key":"1104_CR49","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.1007\/s10462-022-10299-x","volume":"56","author":"A Wong","year":"2023","unstructured":"Wong A, B\u00e4ck T, Kononova AV, Plaat A. Deep multiagent reinforcement learning: challenges and directions. Artif Intell Rev. 2023;56(6):5023\u201356.","journal-title":"Artif Intell Rev"},{"key":"1104_CR50","doi-asserted-by":"crossref","unstructured":"Tan M. Multi-agent reinforcement learning: Independent vs. cooperative agents. In Proceedings of the tenth international conference on machine learning. 1993; pp. 330\u2013337.","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"1104_CR51","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone P, Veloso M. Multiagent systems: a survey from a machine learning perspective. Auton Robot. 2000;8:345\u201383. https:\/\/doi.org\/10.1023\/A:1008942012299.","journal-title":"Auton Robot"},{"key":"1104_CR52","unstructured":"Boutilier C, Price B. Accelerating reinforcement learning through implicit imitation. arXiv e-prints, arXiv-. 2011, 1106."},{"issue":"2\u20133","key":"1104_CR53","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.robot.2004.08.003","volume":"50","author":"JR Kok","year":"2005","unstructured":"Kok JR, Spaan MT, Vlassis N. Non-communicative multi-robot coordination in dynamic environments. Robot Auton Syst. 2005;50(2\u20133):99\u2013114.","journal-title":"Robot Auton Syst"},{"issue":"5","key":"1104_CR54","doi-asserted-by":"publisher","first-page":"755","DOI":"10.7307\/ptt.v35i5.246","volume":"35","author":"H Tuan Trinh","year":"2023","unstructured":"Tuan Trinh H, Bae SH, Duy Tran Q. Improving traffic efficiency in a road network by adopting decentralised multi-agent reinforcement learning and smart navigation. Promet-Traffic Transport. 2023;35(5):755\u201371.","journal-title":"Promet-Traffic Transport"},{"issue":"4","key":"1104_CR55","doi-asserted-by":"publisher","first-page":"7461","DOI":"10.1109\/LRA.2021.3097660","volume":"6","author":"G Ji","year":"2021","unstructured":"Ji G, Yan J, Du J, Yan W, Chen J, Lu Y, et al. Towards safe control of continuum manipulator using shielded multiagent reinforcement learning. IEEE Robot Autom Lett. 2021;6(4):7461\u20138.","journal-title":"IEEE Robot Autom Lett."},{"key":"1104_CR56","doi-asserted-by":"publisher","unstructured":"Rasheed F, Yau KLA, Noor RM, Chong YW. Deep reinforcement learning for addressing disruptions in traffic light control. Comput Mater Continua. 2022. https:\/\/doi.org\/10.32604\/cmc.2022.022952","DOI":"10.32604\/cmc.2022.022952"},{"key":"1104_CR57","unstructured":"Jozefowicz, R., Zaremba, W., & Sutskever, I. An empirical exploration of recurrent network architectures. In International conference on machine learning. PMLR; 2015. pp. 2342\u20132350."},{"key":"1104_CR58","unstructured":"Radford A. Improving language understanding by generative pre-training. 2018."},{"key":"1104_CR59","unstructured":"Yang Z. XLNet: generalized autoregressive pretraining for language understanding. arXiv preprint arXiv. 2019, 1906.08237."},{"key":"1104_CR60","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I","author":"N Carion","year":"2020","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S. End-to-end object detection with transformers. In: Vedaldi A, Bischof H, Brox T, Frahm J-M, editors. Computer vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I. Cham: Springer International Publishing; 2020. p. 213\u201329. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13."},{"key":"1104_CR61","unstructured":"Alexey D. An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv: 2020; 2010.11929."},{"key":"1104_CR62","unstructured":"Vaswani A. Attention is all you need. Adv Neural Inf Process Syst. 2017."},{"key":"1104_CR63","unstructured":"Postnikov A, Gamayunov A, Ferrer G. Transformer based trajectory prediction. arXiv preprint arXiv:2112.04350. 2021."},{"key":"1104_CR64","doi-asserted-by":"crossref","unstructured":"Wei H, Xu N, Zhang H, Zheng G, Zang X, Chen C, et al. Colight: learning network-level cooperation for traffic signal control. In Proceedings of the 28th ACM international conference on information and knowledge management. 2019, pp. 1913\u20131922.","DOI":"10.1145\/3357384.3357902"},{"key":"1104_CR65","doi-asserted-by":"crossref","unstructured":"Lou Y, Wu J, Ran Y. Meta-reinforcement learning for multiple traffic signals control. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022; pp. 4264\u20134268.","DOI":"10.1145\/3511808.3557640"},{"issue":"1","key":"1104_CR66","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s40537-023-00876-4","volume":"11","author":"B Khemani","year":"2024","unstructured":"Khemani B, Patil S, Kotecha K, Tanwar S. A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. J Big Data. 2024;11(1):18.","journal-title":"J Big Data"},{"issue":"1","key":"1104_CR67","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s40537-024-00884-y","volume":"11","author":"MM El-Gayar","year":"2024","unstructured":"El-Gayar MM, Abouhawwash M, Askar SS, Sweidan S. A novel approach for detecting deep fake videos using graph neural network. J Big Data. 2024;11(1):22.","journal-title":"J Big Data"},{"key":"1104_CR68","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. 2016."},{"issue":"1","key":"1104_CR69","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2020","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst. 2020;32(1):4\u201324.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"8","key":"1104_CR70","doi-asserted-by":"publisher","first-page":"8846","DOI":"10.1109\/TITS.2023.3257759","volume":"24","author":"S Rahmani","year":"2023","unstructured":"Rahmani S, Baghbani A, Bouguila N, Patterson Z. Graph neural networks for intelligent transportation systems: a survey. IEEE Trans Intell Transp Syst. 2023;24(8):8846\u201385.","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"8","key":"1104_CR71","doi-asserted-by":"publisher","first-page":"11789","DOI":"10.1109\/TITS.2021.3107258","volume":"23","author":"D Ma","year":"2021","unstructured":"Ma D, Zhou B, Song X, Dai H. A deep reinforcement learning approach to traffic signal control with temporal traffic pattern mining. IEEE Trans Intell Transp Syst. 2021;23(8):11789\u2013800.","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1104_CR72","doi-asserted-by":"crossref","unstructured":"Zheng G, Xiong Y, Zang X, Feng J, Wei H, Zhang H, et al. Learning phase competition for traffic signal control. In Proceedings of the 28th ACM international conference on information and knowledge management. 2019, pp. 1963\u20131972.","DOI":"10.1145\/3357384.3357900"},{"key":"1104_CR73","doi-asserted-by":"crossref","unstructured":"Shabestary SMA, Abdulhai B. Deep learning vs. discrete reinforcement learning for adaptive traffic signal control. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE; 2018, pp. 286\u2013293.","DOI":"10.1109\/ITSC.2018.8569549"},{"issue":"1","key":"1104_CR74","first-page":"6505893","volume":"2020","author":"D Li","year":"2020","unstructured":"Li D, Wu J, Xu M, Wang Z, Hu K. Adaptive traffic signal control model on intersections based on deep reinforcement learning. J Adv Transp. 2020;2020(1):6505893.","journal-title":"J Adv Transp"},{"key":"1104_CR75","unstructured":"Muresan M, Fu L, Pan G. Adaptive traffic signal control with deep reinforcement learning an exploratory investigation. arXiv preprint arXiv:1901.00960. 2019."},{"key":"1104_CR76","unstructured":"Vidali A, Crociani L, Vizzari G, Bandini S. A deep reinforcement learning approach to adaptive traffic lights management. In Woa. 2019, pp. 42\u201350."},{"key":"1104_CR77","unstructured":"Wiering M, Van Veenen J, Vreeken J, Koopman A. Intelligent traffic light control. Institute of Information and Computing Sciences. Utrecht University. 2004."},{"key":"1104_CR78","unstructured":"Van der Pol E, Oliehoek FA. Coordinated deep reinforcement learners for traffic light control. Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016). 2016, 8: 21\u201338."},{"key":"1104_CR79","doi-asserted-by":"crossref","unstructured":"Arulkumaran K, Deisenroth MP, Brundage M, Bharath AA. A brief survey of deep reinforcement learning. arXiv preprint arXiv:1708.05866. 2017.","DOI":"10.1109\/MSP.2017.2743240"},{"key":"1104_CR80","doi-asserted-by":"crossref","unstructured":"Haydari A, Zhang M, Chuah CN, Ghosal D. Impact of deep rl-based traffic signal control on air quality. In 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring). IEEE; 2021, pp. 1\u20136.","DOI":"10.1109\/VTC2021-Spring51267.2021.9448639"},{"key":"1104_CR81","doi-asserted-by":"crossref","unstructured":"P\u00e1los P, Husz\u00e1k \u00c1. Comparison of q-learning based traffic light control methods and objective functions. In 2020 International Conference on Software, Telecommunications and Computer Networks (SoftCOM). IEEE;2020, pp. 1\u20136.","DOI":"10.23919\/SoftCOM50211.2020.9238290"},{"key":"1104_CR82","unstructured":"Li Z, Xu C, Zhang G. A deep reinforcement learning approach for traffic signal control optimization. arXiv preprint arXiv:2107.06115. 2021."},{"key":"1104_CR83","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.future.2020.03.065","volume":"109","author":"F Rasheed","year":"2020","unstructured":"Rasheed F, Yau KLA, Low YC. Deep reinforcement learning for traffic signal control under disturbances: a case study on Sunway city, Malaysia. Future Gener Comput Syst. 2020;109:431\u201345.","journal-title":"Future Gener Comput Syst"},{"issue":"8","key":"1104_CR84","doi-asserted-by":"publisher","first-page":"1428","DOI":"10.1049\/itr2.12521","volume":"18","author":"TY Hu","year":"2024","unstructured":"Hu TY, Li ZY. A multi-agent deep reinforcement learning approach for traffic signal coordination. IET Intel Transport Syst. 2024;18(8):1428\u201344.","journal-title":"IET Intel Transport Syst"},{"issue":"4","key":"1104_CR85","doi-asserted-by":"publisher","first-page":"3479","DOI":"10.3390\/su15043479","volume":"15","author":"M Kolat","year":"2023","unstructured":"Kolat M, K\u0151v\u00e1ri B, B\u00e9csi T, Aradi S. Multi-agent reinforcement learning for traffic signal control: a cooperative approach. Sustainability. 2023;15(4):3479.","journal-title":"Sustainability"},{"key":"1104_CR86","doi-asserted-by":"crossref","unstructured":"Liu Y, Liu L, Chen WP. Intelligent traffic light control using distributed multi-agent Q learning. In 2017 IEEE 20th international conference on intelligent transportation systems (ITSC). IEEE; 2017. pp. 1\u20138.","DOI":"10.1109\/ITSC.2017.8317730"},{"issue":"2","key":"1104_CR87","first-page":"412","volume":"12","author":"LA Prashanth","year":"2010","unstructured":"Prashanth LA, Bhatnagar S. Reinforcement learning with function approximation for traffic signal control. IEEE Trans Intell Transp Syst. 2010;12(2):412\u201321.","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1104_CR88","unstructured":"Hamilton W, Ying Z, Leskovec J. Inductive representation learning on large graphs. Adv Neural Inf Process Syst. 2017;30."},{"key":"1104_CR89","doi-asserted-by":"crossref","unstructured":"Jiang H, Li Z, Wei H, Xiong X, Ruan J, Lu J, et al. X-Light: cross-city traffic signal control using transformer on transformer as meta multi-agent reinforcement learner. arXiv preprint arXiv:2404.12090. 2024.","DOI":"10.24963\/ijcai.2024\/11"},{"key":"1104_CR90","doi-asserted-by":"crossref","unstructured":"Kargar E, Kyrki V. Vision transformer for learning driving policies in complex multi-agent environments. arXiv preprint arXiv:2109.06514. 2021.","DOI":"10.1109\/IV51971.2022.9827348"},{"issue":"11","key":"1104_CR91","doi-asserted-by":"publisher","first-page":"22343","DOI":"10.1109\/TITS.2022.3164450","volume":"23","author":"K Zhang","year":"2022","unstructured":"Zhang K, Feng X, Wu L, He Z. Trajectory prediction for autonomous driving using spatial-temporal graph attention transformer. IEEE Trans Intell Transp Syst. 2022;23(11):22343\u201353.","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"22","key":"1104_CR92","doi-asserted-by":"publisher","first-page":"10870","DOI":"10.3390\/app112210870","volume":"11","author":"AM Ibrahim","year":"2021","unstructured":"Ibrahim AM, Yau KLA, Chong YW, Wu C. Applications of multi-agent deep reinforcement learning: models and algorithms. Appl Sci. 2021;11(22):10870.","journal-title":"Appl Sci"},{"issue":"8","key":"1104_CR93","doi-asserted-by":"publisher","first-page":"8243","DOI":"10.1109\/TVT.2020.2997896","volume":"69","author":"T Wu","year":"2020","unstructured":"Wu T, Zhou P, Liu K, Yuan Y, Wang X, Huang H, Wu DO. Multi-agent deep reinforcement learning for urban traffic light control in vehicular networks. IEEE Trans Vehicular Technol. 2020;69(8):8243\u201356.","journal-title":"IEEE Trans Vehicular Technol"},{"issue":"1","key":"1104_CR94","first-page":"151","volume":"37","author":"WEI Lu","year":"2025","unstructured":"Lu WEI, Zhang X, Lijun FAN, Lei GAO, Jian YANG. IALight: ImportanceAware multi-agent reinforcement learning for arterial traffic cooperative control. Promet Traffic Transport. 2025;37(1):151\u201369.","journal-title":"Promet Traffic Transport"},{"key":"1104_CR95","unstructured":"Ma J, Wu F (2022) Feudal multi-agent reinforcement learning with adaptive network partition for traffic signal control. arXiv preprint arXiv:2205.13836."},{"key":"1104_CR96","doi-asserted-by":"publisher","first-page":"57037","DOI":"10.1109\/ACCESS.2023.3283218","volume":"11","author":"JA Guzm\u00e1n","year":"2023","unstructured":"Guzm\u00e1n JA, Pizarro G, N\u00fa\u00f1ez F. A reinforcement learning-based distributed control scheme for cooperative intersection traffic control. IEEE Access. 2023;11:57037\u201345.","journal-title":"IEEE Access"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01104-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40537-025-01104-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-025-01104-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T12:37:01Z","timestamp":1744202221000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-025-01104-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,7]]},"references-count":96,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1104"],"URL":"https:\/\/doi.org\/10.1186\/s40537-025-01104-x","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3225879\/v1","asserted-by":"object"}]},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,7]]},"assertion":[{"value":"1 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors gave consent for publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"84"}}