{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:30:45Z","timestamp":1782315045919,"version":"3.54.5"},"reference-count":37,"publisher":"Institute for Operations Research and the Management Sciences (INFORMS)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["INFORMS Journal on Computing"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:p>Autonomous mobility-on-demand systems are a viable alternative to mitigate many transportation-related externalities in cities, such as rising vehicle volumes in urban areas and transportation-related pollution. However, the success of these systems heavily depends on efficient and effective fleet control strategies. In this context, we study online control algorithms for autonomous mobility-on-demand systems and develop a novel hybrid combinatorial optimization-enriched machine learning pipeline which learns online dispatching and rebalancing policies from optimal full-information solutions. We test our hybrid pipeline on large-scale real-world scenarios with different vehicle fleet sizes and various request densities. We show that our pipeline outperforms greedy and model-predictive control approaches with respect to various key performance indicators (KPIs), for example, by up to 17.1% and on average by 6.3% in terms of realized profit, and on average by 4.7% in terms of satisfied customers.<\/jats:p>\n                  <jats:p>History: Accepted by Andrea Lodi, Area Editor for Design &amp; Analysis of Algorithms\u2013Discrete.<\/jats:p>\n                  <jats:p>Funding: This work was supported by Deutsche Forschungsgemeinschaft [Grant 449261765].<\/jats:p>\n                  <jats:p>Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https:\/\/pubsonline.informs.org\/doi\/suppl\/10.1287\/ijoc.2024.0637 ) as well as from the IJOC GitHub software repository ( https:\/\/github.com\/INFORMSJoC\/2024.0637 ). The complete IJOC Software and Data Repository is available at https:\/\/informsjoc.github.io\/ .<\/jats:p>","DOI":"10.1287\/ijoc.2024.0637","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T12:14:41Z","timestamp":1749471281000},"page":"745-765","source":"Crossref","is-referenced-by-count":5,"title":["Learning-Based Online Optimization for Autonomous Mobility-on-Demand Fleet Control"],"prefix":"10.1287","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6625-9942","authenticated-orcid":false,"given":"Kai","family":"Jungel","sequence":"first","affiliation":[{"name":"TUM School of Management, Technical University of Munich, 80333 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1762-4947","authenticated-orcid":false,"given":"Axel","family":"Parmentier","sequence":"additional","affiliation":[{"name":"CERMICS, \u00c9cole des Ponts, 77455 Marne-la-Vall\u00e9e, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2682-4975","authenticated-orcid":false,"given":"Maximilian","family":"Schiffer","sequence":"additional","affiliation":[{"name":"TUM School of Management, Technical University of Munich, 80333 Munich, Germany; and Munich Data Science Institute, Technical University of Munich, 80333 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5183-8485","authenticated-orcid":false,"given":"Thibaut","family":"Vidal","sequence":"additional","affiliation":[{"name":"CIRRELT & SCALE-AI Chair in Data-Driven Supply Chains, Department of Mathematics and Industrial Engineering, \u00c9cole Polytechnique de Montr\u00e9al, Montr\u00e9al, Quebec H3T 1J4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"109","reference":[{"key":"B1","doi-asserted-by":"crossref","unstructured":"Alonso-Mora J, Wallar A, Rus D (2017) Predictive routing for autonomous mobility-on-demand systems with ride-sharing.\n                      2017 IEEE\/RSJ Internat. Conf. Intelligent Robots Systems (IROS)\n                      (IEEE, New York), 3583\u20133590.","DOI":"10.1109\/IROS.2017.8206203"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"B3","unstructured":"Berthet Q, Blondel M, Teboul O, Cuturi M, Vert JP, Bach F (2020) Learning with differentiable perturbed optimizers. Larochelle H, Ranzato M, Hadsell R, Balcan M, Lin H, eds.\n                      Advances in Neural Information Processing Systems\n                      , vol. 33 (Curran Associates, Inc. Red Hook, NY), 9508\u20139519."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1763"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranpol.2017.09.005"},{"key":"B6","unstructured":"Dalle G, Baty L, Bouvier L, Parmentier A (2022) Learning with combinatorial optimization layers: A probabilistic approach. Preprint, submitted July 27, https:\/\/arxiv.org\/abs\/2207.13513."},{"key":"B7","unstructured":"Donti P, Amos B, Kolter JZ (2017) Task-based end-to-end model learning in stochastic optimization. Guyon I, Von Luxburg U, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R, eds.\n                      Advances in Neural Information Processing Systems\n                      , vol. 30 (Curran Associates, Inc. Red Hook, NY), 5484\u20135494."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2020.3922"},{"key":"B9","unstructured":"Enders T, Harrison J, Pavone M, Schiffer M (2023) Hybrid multi-agent deep reinforcement learning for autonomous mobility on demand systems. Matni N, Morari M, Pappas GJ, eds.\n                      Proc. 5th Annual Learn. Dynam. Control Conf.\n                      , Proceedings of Machine Learning Research, vol. 211 (PMLR, New York), 1284\u20131296."},{"key":"B10","doi-asserted-by":"crossref","unstructured":"Gammelli D, Yang K, Harrison J, Rodrigues F, Pereira FC, Pavone M (2021) Graph neural network reinforcement learning for autonomous mobility-on-demand systems.\n                      2021 60th IEEE Conf. Decision Control (CDC)\n                      (IEEE, New York), 2996\u20133003.","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"B11","doi-asserted-by":"crossref","unstructured":"Iglesias R, Rossi F, Wang K, Hallac D, Leskovec J, Pavone M (2018) Data-driven model predictive control of autonomous mobility-on-demand systems.\n                      2018 IEEE Internat. Conf. Robotics Automation (ICRA)\n                      (IEEE, New York), 6019\u20136025.","DOI":"10.1109\/ICRA.2018.8460966"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103289"},{"key":"B13","doi-asserted-by":"crossref","unstructured":"Jungel K, Parmentier A, Schiffer M, Vidal T (2025) Learning-based online optimization for autonomous mobility-on-demand fleet control. https:\/\/doi.org\/10.1287\/ijoc.2024.0637.cd, https:\/\/github.com\/INFORMSJoC\/2024.0637.","DOI":"10.1287\/ijoc.2024.0637.cd"},{"key":"B14","doi-asserted-by":"crossref","unstructured":"Kotary J, Fioretto F, Van Hentenryck P, Wilder B (2021) End-to-end constrained optimization learning: A survey. Zhou ZH, ed.\n                      Proc. 30th Internat. Joint Conf. Artificial Intelligence IJCAI-21\n                      (International Joint Conferences on Artificial Intelligence Organization), 4475\u20134482.","DOI":"10.24963\/ijcai.2021\/610"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1186\/1476-069X-9-65"},{"key":"B16","doi-asserted-by":"crossref","unstructured":"Li M, Qin Z, Jiao Y, Yang Y, Wang J, Wang C, Wu G, Ye J (2019) Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning.\n                      World Wide Web Conf.\n                      (Association for Computing Machinery, New York), 983\u2013994.","DOI":"10.1145\/3308558.3313433"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3060187"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3016128"},{"key":"B19","unstructured":"New York City Taxi & Limousine Commission (2015) TLC trip record data. https:\/\/www1.nyc.gov\/site\/tlc\/about\/tlc-trip-record-data.page."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1561\/0600000033"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2094"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.06.040"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-45854-9_19"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912444766"},{"key":"B25","doi-asserted-by":"crossref","unstructured":"Sadeghi Eshkevari S, Tang X, Qin Z, Mei J, Zhang C, Meng Q, Xu J (2022) Reinforcement learning in the wild: Scalable RL dispatching algorithm deployed in ridehailing marketplace.\n                      KDD \u201822 Proc. 28th ACM SIGKDD Conf. Knowledge Discovery Data Mining\n                      (Association for Computing Machinery, New York), 3838\u20133848.","DOI":"10.1145\/3534678.3539095"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2020.11.001"},{"key":"B27","unstructured":"Schrank D, Eisele B, Lomax T (2019) 2019 urban mobility report. Technical report, Texas A&M Transportation Institute, College Station."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3108733"},{"key":"B29","unstructured":"Statista (2021) Market share of the leading ride-hailing companies in the United States from September 2017 to July 2021. https:\/\/www.statista.com\/statistics\/910704\/market-share-of-rideshare-companies-united-states\/."},{"key":"B30","doi-asserted-by":"crossref","unstructured":"Tang X, Qin ZT, Zhang F, Wang Z, Xu Z, Ma Y, Zhu H, Ye J (2019) A deep value-network based approach for multi-driver order dispatching.\n                      KDD \u201819 Proc. 25th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining\n                      (Association for Computing Machinery, New York), 1780\u20131790.","DOI":"10.1145\/3292500.3330724"},{"key":"B31","doi-asserted-by":"crossref","unstructured":"Tsao M, Iglesias R, Pavone M (2018) Stochastic model predictive control for autonomous mobility on demand.\n                      2018 21st Internat. Conf. Intelligent Transportation Systems (ITSC)\n                      (IEEE, New York), 3941\u20133948.","DOI":"10.1109\/ITSC.2018.8569459"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.10.010"},{"key":"B33","unstructured":"White J (2020) Waymo opens driverless robo-taxi service to the public in Phoenix.\n                      Reuters\n                      (October 8), https:\/\/www.reuters.com\/article\/us-waymo-autonomous-phoenix-idUKKBN26T2Y3."},{"key":"B34","doi-asserted-by":"crossref","unstructured":"Xu Z, Li Z, Guan Q, Zhang D, Li Q, Nan J, Liu C, Bian W, Ye J (2018) Large-scale order dispatch in on-demand ride-hailing platforms: A learning and planning approach.\n                      KDD \u201818 Proc. 24th ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining\n                      (Association for Computing Machinery, New York), 905\u2013913.","DOI":"10.1145\/3219819.3219824"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-012811"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581863"},{"key":"B37","doi-asserted-by":"crossref","unstructured":"Zhou M, Jin J, Zhang W, Qin Z, Jiao Y, Wang C, Wu G, Yu Y, Ye J (2019) Multi-agent reinforcement learning for order-dispatching via order-vehicle distribution matching.\n                      CIKM \u201819 Proc. 28th ACM Internat. Conf. Inform. Knowledge Management\n                      (Association for Computing Machinery, New York), 2645\u20132653.","DOI":"10.1145\/3357384.3357799"}],"container-title":["INFORMS Journal on Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubsonline.informs.org\/doi\/pdf\/10.1287\/ijoc.2024.0637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T08:54:50Z","timestamp":1781513690000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubsonline.informs.org\/doi\/10.1287\/ijoc.2024.0637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1287\/ijoc.2024.0637"],"URL":"https:\/\/doi.org\/10.1287\/ijoc.2024.0637","relation":{},"ISSN":["1091-9856","1526-5528"],"issn-type":[{"value":"1091-9856","type":"print"},{"value":"1526-5528","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}