{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:51:10Z","timestamp":1784335870897,"version":"3.55.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100014718","name":"Innovative Research Group Project of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62466004,61962007,62266009,61462008,61751213,61866004"],"award-info":[{"award-number":["62466004,61962007,62266009,61462008,61751213,61866004"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2018GXNSFDA294001, 2018GXNSFDA281009"],"award-info":[{"award-number":["2018GXNSFDA294001, 2018GXNSFDA281009"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Key Laboratory of Big Data in Finance and Economicsization and Big Data Processing","award":["No.FEDOP2022A06"],"award-info":[{"award-number":["No.FEDOP2022A06"]}]},{"name":"2020 Guangxi Education Department Degree and Postgraduate Education Reform Project","award":["20210121210028"],"award-info":[{"award-number":["20210121210028"]}]},{"name":"Research Fund of Guangxi Key Lab of Multi-source Information Mining Security","award":["MIMS19-04"],"award-info":[{"award-number":["MIMS19-04"]}]},{"name":"2015 Innovation Team Project of Guangxi University of Science and Technology of Science and Technology","award":["gxkjdx201504"],"award-info":[{"award-number":["gxkjdx201504"]}]},{"name":"College Students Innovative Entrepreneurial Training","award":["202210594036, 202210594037, 202210594038, 202210594041, 202110594133, 202110594134"],"award-info":[{"award-number":["202210594036, 202210594037, 202210594038, 202210594041, 202110594133, 202110594134"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10489-025-06359-8","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T07:00:16Z","timestamp":1741676416000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DiffusionLight:a multi-agent reinforcement learning approach for traffic signal control based on shortcut-diffusion model"],"prefix":"10.1007","volume":"55","author":[{"given":"JiLin","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2309-7282","authenticated-orcid":false,"given":"Zhiwen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruonan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"6359_CR1","doi-asserted-by":"crossref","unstructured":"Bauschke HH, Combettes PL (2011) Convex analysis and monotone operator theory in hilbert spaces. In: CMS books in mathematics, pp 1\u2013468","DOI":"10.1007\/978-1-4419-9467-7_1"},{"key":"6359_CR2","doi-asserted-by":"crossref","unstructured":"Chen C, Wei H, Xu N, et\u00a0al (2020) Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control, pp 3414\u20133421","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"6359_CR3","unstructured":"Chen H, Jiang Y, Guo S, et\u00a0al (2024) Difflight: a partial rewards conditioned diffusion model for traffic signal control with missing data. arXiv:2410.22938"},{"key":"6359_CR4","doi-asserted-by":"crossref","unstructured":"Chung H, Sim B, Ye JC (2022) Come-closer-diffuse-faster: accelerating conditional diffusion models for inverse problems through stochastic contraction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12413\u201312422","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"6359_CR5","doi-asserted-by":"crossref","unstructured":"Dey R, Salem FM (2017) Gate-variants of gated recurrent unit (gru) neural networks. In: 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), IEEE, pp 1597\u20131600","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"6359_CR6","doi-asserted-by":"crossref","unstructured":"Foerster J, Farquhar G, Afouras T, et\u00a0al (2018) Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"6359_CR7","doi-asserted-by":"crossref","unstructured":"Gronauer S, Diepold K (2022) Multi-agent deep reinforcement learning: a survey. Artificial Intelligence Review, pp 1\u201349","DOI":"10.1007\/s10462-021-09996-w"},{"key":"6359_CR8","unstructured":"Haarnoja T, Zhou A, Abbeel P, et\u00a0al (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, PMLR, pp 1861\u20131870"},{"key":"6359_CR9","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. arXiv:2006.11239"},{"issue":"1","key":"6359_CR10","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1038\/scientificamerican0792-66","volume":"267","author":"JH Holland","year":"1992","unstructured":"Holland JH (1992) Genetic algorithms. Sci American 267(1):66\u201373","journal-title":"Sci American"},{"key":"6359_CR11","unstructured":"Jiang H, Li Z, Wei H, et\u00a0al (2024) X-light: cross-city traffic signal control using transformer on transformer as meta multi-agent reinforcement learner. arXiv:2404.12090"},{"key":"6359_CR12","doi-asserted-by":"crossref","unstructured":"Jiang J, Han C, Zhao WX, et\u00a0al (2023) Pdformer: propagation delay-aware dynamic long-range transformer for traffic flow prediction. In: Proceedings of the AAAI conference on artificial intelligence, pp 4365\u20134373","DOI":"10.1609\/aaai.v37i4.25556"},{"key":"6359_CR13","doi-asserted-by":"crossref","unstructured":"Li C, Ma X, Xia L, et\u00a0al (2020) Fairness control of traffic light via deep reinforcement learning. In: 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), pp 652\u2013658","DOI":"10.1109\/CASE48305.2020.9216899"},{"key":"6359_CR14","doi-asserted-by":"crossref","unstructured":"Li Z, Yu H, Zhang G, et\u00a0al (2021a) Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning. arXiv:2104.09936","DOI":"10.1016\/j.trc.2021.103059"},{"key":"6359_CR15","doi-asserted-by":"publisher","first-page":"103059","DOI":"10.1016\/j.trc.2021.103059","volume":"125","author":"Z Li","year":"2021","unstructured":"Li Z, Yu H, Zhang G et al (2021) Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning. Trans Res Part C: Emerg Technol 125:103059","journal-title":"Trans Res Part C: Emerg Technol"},{"key":"6359_CR16","doi-asserted-by":"crossref","unstructured":"Liang E, Su Z, Fang C, et\u00a0al (2022) Oam: an option-action reinforcement learning framework for universal multi-intersection control. In: Proceedings of the AAAI conference on artificial intelligence, pp 4550\u20134558","DOI":"10.1609\/aaai.v36i4.20378"},{"key":"6359_CR17","unstructured":"Lowe R, Wu YI, Tamar A, et\u00a0al (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. Advan Neural Inform Process Syst 30"},{"key":"6359_CR18","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1109\/TITS.2022.3229477","volume":"24","author":"F Mao","year":"2023","unstructured":"Mao F, Li Z, Lin Y et al (2023) Mastering arterial traffic signal control with multi-agent attention-based soft actor-critic model. IEEE Trans Intell Transp Syst 24:3129\u20133144","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6359_CR19","doi-asserted-by":"crossref","unstructured":"Mei H, Lei X, Da L, et\u00a0al (2022) Libsignal: An open library for traffic signal control. arXiv:2211.10649","DOI":"10.1007\/s10994-023-06412-y"},{"key":"6359_CR20","doi-asserted-by":"crossref","unstructured":"Mei H, Li J, Shi B, et\u00a0al (2023) Reinforcement learning approaches for traffic signal control under missing data. arXiv:2304.10722","DOI":"10.24963\/ijcai.2023\/251"},{"key":"6359_CR21","first-page":"4079","volume":"33","author":"A Oroojlooy","year":"2020","unstructured":"Oroojlooy A, Nazari M, Hajinezhad D et al (2020) Attendlight: Universal attention-based reinforcement learning model for traffic signal control. Adv Neural Inf Process Syst 33:4079\u20134090","journal-title":"Adv Neural Inf Process Syst"},{"key":"6359_CR22","doi-asserted-by":"crossref","unstructured":"Pham QC (2008) Analysis of discrete and hybrid stochastic systems by nonlinear contraction theory. In: 2008 10th International conference on control, automation, robotics and vision, IEEE, pp 1054\u20131059","DOI":"10.1109\/ICARCV.2008.4795665"},{"issue":"4","key":"6359_CR23","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TAC.2008.2009619","volume":"54","author":"QC Pham","year":"2009","unstructured":"Pham QC, Tabareau N, Slotine JJ (2009) A contraction theory approach to stochastic incremental stability. IEEE Trans Autom Control 54(4):816\u2013820","journal-title":"IEEE Trans Autom Control"},{"key":"6359_CR24","first-page":"10199","volume":"33","author":"T Rashid","year":"2020","unstructured":"Rashid T, Farquhar G, Peng B et al (2020) Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning. Adv Neural Inf Process Syst 33:10199\u201310210","journal-title":"Adv Neural Inf Process Syst"},{"issue":"178","key":"6359_CR25","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid T, Samvelyan M, De Witt CS et al (2020) Monotonic value function factorisation for deep multi-agent reinforcement learning. J Mach Learn Res 21(178):1\u201351","journal-title":"J Mach Learn Res"},{"key":"6359_CR26","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, et\u00a0al (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"6359_CR27","unstructured":"Song J, Meng C, Ermon S (2020a) Denoising diffusion implicit models. arXiv:2010.02502"},{"key":"6359_CR28","unstructured":"Song Y, Sohl-Dickstein J, Kingma DP, et\u00a0al (2020b) Score-based generative modeling through stochastic differential equations. arXiv:2011.13456"},{"key":"6359_CR29","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"6359_CR30","unstructured":"Vaswani A, Shazeer N, Parmar N, et\u00a0al (2017) Attention is all you need. Advan Neural Inform Process Syst 30"},{"key":"6359_CR31","unstructured":"Wang Z, Hunt JJ, Zhou M (2022) Diffusion policies as an expressive policy class for offline reinforcement learning. arXiv:2208.06193"},{"key":"6359_CR32","doi-asserted-by":"crossref","unstructured":"Wei H, Zheng G, Yao H, et\u00a0al (2018) Intellilight: A reinforcement learning approach for intelligent traffic light control. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2496\u20132505","DOI":"10.1145\/3219819.3220096"},{"key":"6359_CR33","doi-asserted-by":"crossref","unstructured":"Wei H, Chen C, Zheng G, et\u00a0al (2019a) Presslight: Learning max pressure control to coordinate traffic signals in arterial network. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 1290\u20131298","DOI":"10.1145\/3292500.3330949"},{"key":"6359_CR34","doi-asserted-by":"crossref","unstructured":"Wei H, Xu N, Zhang H, et\u00a0al (2019b) Colight: Learning network-level cooperation for traffic signal control. Proceedings of the 28th ACM international conference on information and knowledge management","DOI":"10.1145\/3357384.3357902"},{"key":"6359_CR35","unstructured":"Wei H, Zheng G, Gayah V, et\u00a0al (2019c) A survey on traffic signal control methods. arXiv:1904.08117"},{"key":"6359_CR36","unstructured":"Wu Q, Zhang L, Shen J, et\u00a0al (2021) Efficient pressure: Improving efficiency for signalized intersections. arXiv:2112.02336"},{"key":"6359_CR37","doi-asserted-by":"crossref","unstructured":"Zhang H, Feng S, Liu C, et\u00a0al (2019) Cityflow: a multi-agent reinforcement learning environment for large scale city traffic scenario. In: The world wide web conference, pp 3620\u20133624","DOI":"10.1145\/3308558.3314139"},{"key":"6359_CR38","unstructured":"Zhang L, Wu Q, Deng J (2021) Attentionlight: Rethinking queue length and attention mechanism for traffic signal control. arXiv:2201.00006"},{"key":"6359_CR39","doi-asserted-by":"crossref","unstructured":"Zhang L, Rao A, Agrawala M (2023) Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3836\u20133847","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"6359_CR40","doi-asserted-by":"crossref","unstructured":"Zheng G, Xiong Y, Zang X, et\u00a0al (2019a) Learning phase competition for traffic signal control. In: Proceedings of the 28th ACM international conference on information and knowledge management, pp 1963\u20131972","DOI":"10.1145\/3357384.3357900"},{"key":"6359_CR41","unstructured":"Zheng G, Zang X, Xu N, et\u00a0al (2019b) Diagnosing reinforcement learning for traffic signal control. arXiv:1905.04716"},{"key":"6359_CR42","unstructured":"Zhu Z, Liu M, Mao L, et\u00a0al (2023) Madiff: offline multi-agent learning with diffusion models. arXiv:2305.17330"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06359-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06359-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06359-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:32:55Z","timestamp":1758310375000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06359-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":42,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["6359"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06359-8","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]},"assertion":[{"value":"11 February 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors disclosed no relevant relationships.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Consent","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"527"}}