{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:16:49Z","timestamp":1783995409077,"version":"3.55.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004761","name":"the Natural Science Foundation of Hunan Province","doi-asserted-by":"crossref","award":["2024JJ5163"],"award-info":[{"award-number":["2024JJ5163"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Humanities and Social Sciences Project of Ministry of Education of China","award":["24YJAZH237"],"award-info":[{"award-number":["24YJAZH237"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10586-025-05842-8","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T20:30:57Z","timestamp":1762893057000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-agent deep reinforcement learning based on cloud-edge computing for urban vehicle route guidance"],"prefix":"10.1007","volume":"29","author":[{"given":"Zhuhua","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjian","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aiping","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijiang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"5842_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2021.101343","volume":"50","author":"AM Nagy","year":"2021","unstructured":"Nagy, A.M., Simon, V.: Improving traffic prediction using congestion propagation patterns in smart cities [J]. Advanced Engineering Informatics 50, 101343 (2021)","journal-title":"Advanced Engineering Informatics"},{"key":"5842_CR2","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.engappai.2016.01.001","volume":"52","author":"E Walraven","year":"2016","unstructured":"Walraven, E., Spaan, M.T., Bakker, B.: Traffic flow optimization: A reinforcement learning approach [J]. Engineering Applications of Artificial Intelligence 52, 203\u2013212 (2016)","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"7","key":"5842_CR3","doi-asserted-by":"publisher","first-page":"7190","DOI":"10.1109\/TITS.2023.3263904","volume":"24","author":"B Wang","year":"2023","unstructured":"Wang, B., Zhang, Y., Shi, J., Wang, P., Wang, X., Bai, L., Wang, Y.: Knowledge expansion and consolidation for continual traffic prediction with expanding graphs [J]. IEEE Transactions on Intelligent Transportation Systems 24(7), 7190\u20137201 (2023)","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"3","key":"5842_CR4","doi-asserted-by":"publisher","first-page":"2551","DOI":"10.1109\/TVT.2016.2572123","volume":"66","author":"J Lin","year":"2017","unstructured":"Lin, J., Yu, W., Yang, X., et al.: A Real-Time En-Route route guidance decision scheme for Transportation-Based cyberphysical systems [J]. IEEE Trans. Veh. Technol. 66(3), 2551\u20132566 (2017)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"5842_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128423","volume":"608","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Zhao, W., Wang, J., Yuan, Y.: Recent progress, challenges and future prospects of applied deep reinforcement learning: A practical perspective in path planning [J]. Neurocomputing 608, 128423 (2024)","journal-title":"Neurocomputing"},{"issue":"6","key":"5842_CR6","doi-asserted-by":"publisher","first-page":"5446","DOI":"10.1109\/TITS.2021.3053958","volume":"23","author":"L Luo","year":"2021","unstructured":"Luo, L., Sheng, L., Yu, H., et al.: Intersection-based V2X routing via reinforcement learning in vehicular ad hoc networks [J]. IEEE Trans. Intell. Transp. Syst. 23(6), 5446\u20135459 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"5842_CR7","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MWC.001.1900151","volume":"26","author":"A Ahmad","year":"2019","unstructured":"Ahmad, A., Din, S., Paul, A., et al.: Real-Time route planning and data dissemination for urban scenarios using the internet of things [J]. IEEE Wireless Communications 26(6), 50\u201355 (2019)","journal-title":"IEEE Wireless Communications"},{"key":"5842_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2024.103643","volume":"165","author":"L Zhu","year":"2024","unstructured":"Zhu, L., Li, B., Tan, L.: Vehicular edge cloud computing content caching optimization solution based on content prediction and deep reinforcement learning [J]. Ad Hoc Networks 165, 103643 (2024)","journal-title":"Ad Hoc Networks"},{"key":"5842_CR9","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.trc.2018.06.001","volume":"93","author":"C Mao","year":"2018","unstructured":"Mao, C., Shen, Z.: A reinforcement learning framework for the adaptive routing problem in stochastic time-dependent network [J]. Transp. Res. Part. C: Emerg. Technol. 93, 179\u2013197 (2018)","journal-title":"Transp. Res. Part. C: Emerg. Technol."},{"key":"5842_CR10","doi-asserted-by":"crossref","unstructured":"Arasteh, F., Sheikhgargar, S., Papagelis, M.: Network-aware multi-agent reinforcement learning for the vehicle navigation problem [C]. Proceedings of the 30th International Conference on Advances in Geographic Information Systems ((SIGSPATIAL), 4 pages. (2022)","DOI":"10.1145\/3557915.3561005"},{"key":"5842_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128085","volume":"599","author":"S Du","year":"2024","unstructured":"Du, S., Zhu, Z., Wang, X., et al.: Real-time local path planning strategy based on deep distributional reinforcement learning [J]. Neurocomputing 599, 128085 (2024)","journal-title":"Neurocomputing"},{"key":"5842_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104440","volume":"158","author":"J Shang","year":"2024","unstructured":"Shang, J., Cong, Q.T., Mehdi, K.E.: Regional route guidance with realistic compliance patterns: Application of deep reinforcement learning and MPC [J]. Transp. Res. Part. C: Emerg. Technol. 158, 104440 (2024)","journal-title":"Transp. Res. Part. C: Emerg. Technol."},{"key":"5842_CR13","doi-asserted-by":"publisher","first-page":"104311","DOI":"10.1016\/j.scs.2022.104311","volume":"89","author":"M Khalid","year":"2023","unstructured":"Khalid, M., Wang, L., Wang, K., et al.: Deep reinforcement learning-based long-range autonomous valet parking for smart cities [J]. Sustainable Cities Soc. 89, 104311 (2023)","journal-title":"Sustainable Cities Soc."},{"key":"5842_CR14","doi-asserted-by":"crossref","unstructured":"Lu, J., Li, J., Yuan, Q., et al.: A multi-vehicle cooperative routing method based on evolutionary game theory [C]. Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC), (2019)","DOI":"10.1109\/ITSC.2019.8917441"},{"key":"5842_CR15","doi-asserted-by":"crossref","unstructured":"Dijkstra, E.W.: A note on two problems in connexion with graphs [M]. in: Edsger Wybe Dijkstra: His Life, Work, and Legacy, 287\u2013290. (2022)","DOI":"10.1145\/3544585.3544600"},{"key":"5842_CR16","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, J., Wang, P., Wang, X., Zhang, Y., Zhou, Z., Wang, Y.: Stone: A spatio-temporal ood learning framework kills both spatial and temporal shifts [C]. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 2948\u20132959). (2024), August","DOI":"10.1145\/3637528.3671680"},{"key":"5842_CR17","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.ins.2020.10.012","volume":"555","author":"B Chen","year":"2021","unstructured":"Chen, B., Ding, Z., Wu, Y., et al.: An optimal global algorithm for route guidance in advanced traveler information systems [J]. Information Sciences 555, 33\u201345 (2021)","journal-title":"Information Sciences"},{"key":"5842_CR18","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.is.2016.01.007","volume":"64","author":"T Liebig","year":"2017","unstructured":"Liebig, T., Piatkowski, N., Bockermann, C., et al.: Dynamic route planning with real-time traffic predictions [J]. Inform. Syst. 64, 258\u2013265 (2017)","journal-title":"Inform. Syst."},{"issue":"14","key":"5842_CR19","doi-asserted-by":"publisher","first-page":"12763","DOI":"10.1109\/JIOT.2023.3255200","volume":"10","author":"W Zhu","year":"2023","unstructured":"Zhu, W., Zhu, C., Prediction-based, A.: Route guidance method toward intelligent and green transportation system [J]. IEEE Internet Things J. 10(14), 12763\u201312776 (2023)","journal-title":"IEEE Internet Things J."},{"key":"5842_CR20","doi-asserted-by":"publisher","first-page":"106694","DOI":"10.1016\/j.asoc.2020.106694","volume":"96","author":"S Koh","year":"2020","unstructured":"Koh, S., Zhou, B., Fang, H., et al.: Real-time deep reinforcement learning based vehicle navigation [J]. Appl. Soft Comput. 96, 106694 (2020)","journal-title":"Appl. Soft Comput."},{"key":"5842_CR21","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.future.2018.12.037","volume":"94","author":"D Mukhutdinov","year":"2019","unstructured":"Mukhutdinov, D., Filchenkov, A., Shalyto, A., et al.: Multi-agent deep learning for simultaneous optimization for time and energy in distributed routing system [J]. Future Generation Comput. Syst. 94, 587\u2013600 (2019)","journal-title":"Future Generation Comput. Syst."},{"issue":"5","key":"5842_CR22","doi-asserted-by":"publisher","first-page":"2956","DOI":"10.1109\/TITS.2020.2978227","volume":"22","author":"C Tang","year":"2020","unstructured":"Tang, C., Hu, W., Hu, S., et al.: Urban traffic route guidance method with high adaptive learning ability under diverse traffic scenarios [J]. IEEE Trans. Intell. Transp. Syst. 22(5), 2956\u20132968 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"5842_CR23","doi-asserted-by":"publisher","first-page":"3730","DOI":"10.1109\/TITS.2020.3023958","volume":"22","author":"K Lin","year":"2021","unstructured":"Lin, K., Li, C., Li, Y., et al.: Distributed learning for vehicle routing decision in software defined internet of vehicles [J]. IEEE Trans. Intell. Transp. Syst. 22(6), 3730\u20133741 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"5842_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103560","volume":"137","author":"Z Shou","year":"2022","unstructured":"Shou, Z., Chen, X., Fu, Y., et al.: Multi-agent reinforcement learning for Markov routing games: A new modeling paradigm for dynamic traffic assignment [J]. Transportation Research Part C: Emerging Technologies 137, 103560 (2022)","journal-title":"Transportation Research Part C: Emerging Technologies"},{"issue":"6","key":"5842_CR25","doi-asserted-by":"publisher","first-page":"7180","DOI":"10.1109\/TMC.2023.3332081","volume":"23","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Yu, Z., Zhang, J., et al.: Learning decentralized traffic signal controllers with Multi-Agent graph reinforcement learning [J]. IEEE Trans. Mob. Comput. 23(6), 7180\u20137195 (2024)","journal-title":"IEEE Trans. Mob. Comput."},{"key":"5842_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104663","volume":"164","author":"Y Bie","year":"2024","unstructured":"Bie, Y., Ji, Y., Ma, D.: Multi-agent deep reinforcement learning collaborative traffic signal control method considering intersection heterogeneity [J]. Transportation Research Part C: Emerging Technologies 164, 104663 (2024)","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"5842_CR27","doi-asserted-by":"publisher","first-page":"119484","DOI":"10.1016\/j.ins.2023.119484","volume":"647","author":"J Liu","year":"2023","unstructured":"Liu, J., Qin, S., Su, M., et al.: Multiple intersections traffic signal control based on cooperative multi-agent reinforcement learning [J]. Inf. Sci. 647, 119484 (2023)","journal-title":"Inf. Sci."},{"issue":"4","key":"5842_CR28","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1109\/TITS.2018.2848264","volume":"20","author":"K Menda","year":"2019","unstructured":"Menda, K., Chen, Y.C., Grana, J., et al.: Deep reinforcement learning for Event-Driven Multi-Agent decision processes [J]. IEEE Transactions on Intelligent Transportation Systems 20(4), 1259\u20131268 (2019)","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"5842_CR29","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs [C]. proceedings of the AAAI fall symposium series, (2015)"},{"issue":"4","key":"5842_CR30","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi12040144","volume":"12","author":"Z Liao","year":"2023","unstructured":"Liao, Z., Huang, H., Zhao, Y., et al.: Analysis and forecast of traffic flow between urban functional areas based on Ride-Hailing trajectories [J]. ISPRS International Journal of Geo-Information 12(4), 144 (2023)","journal-title":"ISPRS International Journal of Geo-Information"},{"key":"5842_CR31","doi-asserted-by":"publisher","first-page":"4195","DOI":"10.1007\/s10489-020-01755-8","volume":"50","author":"H Chen","year":"2020","unstructured":"Chen, H., Liu, Y., Zhou, Z., et al.: Gama: Graph attention multi-agent reinforcement learning algorithm for Cooperation [J]. Appl. Intell. 50, 4195\u20134205 (2020)","journal-title":"Appl. Intell."},{"key":"5842_CR32","unstructured":"Veli\u010ckovi\u0106, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. arXiv preprint arXiv:171010903, (2017)"},{"issue":"2","key":"5842_CR33","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1109\/TAC.2020.2986195","volume":"66","author":"T Tanaka","year":"2020","unstructured":"Tanaka, T., Nekouei, E., Pedram, A.R., et al.: Linearly solvable mean-field traffic routing games [J]. IEEE Trans. Autom. Control. 66(2), 880\u2013887 (2020)","journal-title":"IEEE Trans. Autom. Control"},{"key":"5842_CR34","doi-asserted-by":"crossref","unstructured":"Cabannes, T., Lauriere, M., Perolat, J., et al.: Solving N-player dynamic routing games with congestion: A mean field approach. (2021). arXiv preprint arXiv:2110.11943","DOI":"10.65109\/FJNT7466"},{"key":"5842_CR35","unstructured":"Yang, Y., Luo, R., Li, M., et al.: Mean field multi-agent reinforcement learning [C]. International conference on machine learning (ICML), 5571\u20135580. (2018)"},{"issue":"1","key":"5842_CR36","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1109\/JIOT.2023.3289888","volume":"11","author":"J Ren","year":"2023","unstructured":"Ren, J., Zheng, J., Guo, X., et al.: MeFi: Mean field reinforcement learning for cooperative routing in wireless sensor network[J]. IEEE Internet Things J. 11(1), 995\u20131011 (2023)","journal-title":"IEEE Internet Things J."},{"key":"5842_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2023.105065","volume":"101","author":"Y Su","year":"2024","unstructured":"Su, Y., Zhang, T., Xu, M., Tan, M., et al.: Rough knowledge enhanced dueling deep Q-network for household integrated demand response optimization [J]. Sustainable Cities and Society 101, 105065 (2024)","journal-title":"Sustainable Cities and Society"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05842-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-025-05842-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05842-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:08:46Z","timestamp":1773925726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-025-05842-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["5842"],"URL":"https:\/\/doi.org\/10.1007\/s10586-025-05842-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"16 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics declaration"}}],"article-number":"17"}}