{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:00:21Z","timestamp":1767319221085,"version":"3.48.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032091550","type":"print"},{"value":"9783032091567","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-09156-7_1","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:57:35Z","timestamp":1767319055000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-agent Soft Actor-Critic with\u00a0Coordinated Loss for\u00a0Autonomous Mobility-on-Demand Fleet Control"],"prefix":"10.1007","author":[{"given":"Zeno","family":"Woywood","sequence":"first","affiliation":[]},{"given":"Jasper I.","family":"Wiltfang","sequence":"additional","affiliation":[]},{"given":"Julius","family":"Luy","sequence":"additional","affiliation":[]},{"given":"Tobias","family":"Enders","sequence":"additional","affiliation":[]},{"given":"Maximilian","family":"Schiffer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"issue":"3","key":"1_CR1","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1073\/pnas.1611675114","volume":"114","author":"J Alonso-Mora","year":"2017","unstructured":"Alonso-Mora, J., Samaranayake, S., Wallar, A., Frazzoli, E., Rus, D.: On-demand high-capacity ride-sharing via dynamic trip-vehicle assignment. Proc. Natl. Acad. Sci. 114(3), 462\u2013467 (2017). https:\/\/doi.org\/10.1073\/pnas.1611675114","journal-title":"Proc. Natl. Acad. Sci."},{"key":"1_CR2","unstructured":"Chang, Y.H., Ho, T., Kaelbling, L.P.: All learning is local: multi-agent learning in global reward games. In: Proceedings of the 17th International Conference on Neural Information Processing Systems, pp. 807\u2013814. MIT Press (2003)"},{"key":"1_CR3","unstructured":"Christodoulou, P.: Soft actor-critic for discrete action settings. CoRR (2019). http:\/\/arxiv.org\/abs\/1910.07207"},{"key":"1_CR4","unstructured":"Enders, T., Harrison, J., Pavone, M., Schiffer, M.: Hybrid multi-agent deep reinforcement learning for autonomous mobility on demand systems. In: Proceedings of The 5th Annual Learning for Dynamics and Control Conference, pp. 1284\u20131296. PMLR (2023)"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Fluri, C., Ruch, C., Zilly, J., Hakenberg, J., Frazzoli, E.: Learning to operate a fleet of cars. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 2292\u20132298. IEEE Press (2019). https:\/\/doi.org\/10.1109\/ITSC.2019.8917533","DOI":"10.1109\/ITSC.2019.8917533"},{"key":"1_CR6","doi-asserted-by":"publisher","unstructured":"Gammelli, D., Yang, K., Harrison, J., Rodrigues, F., Pereira, F.C., Pavone, M.: Graph neural network reinforcement learning for autonomous mobility-on-demand systems. In: IEEE Conference on Decision and Control (CDC), vol.\u00a060, pp. 2996\u20133003. IEEE Press (2021). https:\/\/doi.org\/10.1109\/CDC45484.2021.9683135","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Holler, J., et al.: Deep reinforcement learning for multi-driver vehicle dispatching and repositioning problem. In: IEEE International Conference on Data Mining (ICDM), pp. 1090\u20131095 (2019). https:\/\/doi.org\/10.1109\/ICDM.2019.00129","DOI":"10.1109\/ICDM.2019.00129"},{"key":"1_CR8","unstructured":"Hoppe, H., Enders, T., Cappart, Q., Schiffer, M.: Global rewards in multi-agent deep reinforcement learning for autonomous mobility on demand systems. In: Proceedings of the 6th Annual Learning for Dynamics &; Control Conference, pp. 260\u2013272. PMLR (2024)"},{"key":"1_CR9","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.trc.2018.05.003","volume":"92","author":"M Hyland","year":"2018","unstructured":"Hyland, M., Mahmassani, H.S.: Dynamic autonomous vehicle fleet operations: optimization-based strategies to assign AVS to immediate traveler demand requests. Transport. Res. Part C: Emerg. Technol. 92, 278\u2013297 (2018). https:\/\/doi.org\/10.1016\/j.trc.2018.05.003","journal-title":"Transport. Res. Part C: Emerg. Technol."},{"key":"1_CR10","doi-asserted-by":"publisher","unstructured":"Iglesias, R., Rossi, F., Wang, K., Hallac, D., Leskovec, J., Pavone, M.: Data-driven model predictive control of autonomous mobility-on-demand systems. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6019\u20136025. IEEE Press (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8460966","DOI":"10.1109\/ICRA.2018.8460966"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"Jiao, Y., et al.: Real-world ride-hailing vehicle repositioning using deep reinforcement learning. Transport. Res. Part C: Emerg. Technol. 130 (2021). https:\/\/doi.org\/10.1016\/j.trc.2021.103289","DOI":"10.1016\/j.trc.2021.103289"},{"key":"1_CR12","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2024.0637","author":"K Jungel","year":"2025","unstructured":"Jungel, K., Parmentier, A., Schiffer, M., Vidal, T.: Learning-based online optimization for autonomous mobility-on-demand fleet control. INFORMS J. Comput. (2025). https:\/\/doi.org\/10.1287\/ijoc.2024.0637","journal-title":"INFORMS J. Comput."},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Li, B., Ammar, N., Tiwari, P., Peng, H.: Decentralized ride-sharing of shared autonomous vehicles using graph neural network-based reinforcement learning. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 912\u2013918 (2022). https:\/\/doi.org\/10.1109\/ICRA46639.2022.9811596","DOI":"10.1109\/ICRA46639.2022.9811596"},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning. In: The World Wide Web Conference, pp. 983\u2013994. ACM (2019). https:\/\/doi.org\/10.1145\/3308558.3313433","DOI":"10.1145\/3308558.3313433"},{"issue":"9","key":"1_CR15","doi-asserted-by":"publisher","first-page":"4742","DOI":"10.1109\/TNNLS.2021.3060187","volume":"33","author":"E Liang","year":"2022","unstructured":"Liang, E., Wen, K., Lam, W.H.K., Sumalee, A., Zhong, R.: An integrated reinforcement learning and centralized programming approach for online taxi dispatching. IEEE Trans. Neural Netw. Learn. Syst. 33(9), 4742\u20134756 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2021.3060187","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1996","DOI":"10.1109\/TITS.2020.3030252","volume":"23","author":"Z Liu","year":"2022","unstructured":"Liu, Z., Li, J., Wu, K.: Context-aware taxi dispatching at city-scale using deep reinforcement learning. IEEE Trans. Intell. Transp. Syst. 23(3), 1996\u20132009 (2022). https:\/\/doi.org\/10.1109\/TITS.2020.3030252","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"5","key":"1_CR17","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1287\/inte.2020.1047","volume":"50","author":"ZT Qin","year":"2020","unstructured":"Qin, Z.T., et al.: Ride-hailing order dispatching at didi via reinforcement learning. INFORMS J. Appl. Anal. 50(5), 272\u2013286 (2020). https:\/\/doi.org\/10.1287\/inte.2020.1047","journal-title":"INFORMS J. Appl. Anal."},{"key":"1_CR18","doi-asserted-by":"publisher","unstructured":"Tang, X., et al.: A deep value-network based approach for multi-driver order dispatching. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1780\u20131790. ACM (2019). https:\/\/doi.org\/10.1145\/3292500.3330724","DOI":"10.1145\/3292500.3330724"},{"key":"1_CR19","unstructured":"TLC, N.: Trip record data (2015). https:\/\/www.nyc.gov\/site\/tlc\/about\/tlc-trip-record-data.page"},{"key":"1_CR20","doi-asserted-by":"publisher","unstructured":"Zheng, B., Ming, L., Hu, Q., L\u00fc, Z., Liu, G., Zhou, X.: Supply-demand-aware deep reinforcement learning for dynamic fleet management. ACM Trans. Intell. Syst. Technol. 13(3) (2022). https:\/\/doi.org\/10.1145\/3467979","DOI":"10.1145\/3467979"},{"key":"1_CR21","doi-asserted-by":"publisher","unstructured":"Zhou, M., et al.: Multi-agent reinforcement learning for order-dispatching via order-vehicle distribution matching. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2645\u20132653. ACM (2019). https:\/\/doi.org\/10.1145\/3357384.3357799","DOI":"10.1145\/3357384.3357799"}],"container-title":["Lecture Notes in Computer Science","Learning and Intelligent Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09156-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:57:36Z","timestamp":1767319056000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09156-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032091550","9783032091567"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09156-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"LION","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Learning and Intelligent Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lion2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lion19.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}