{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:19:40Z","timestamp":1783149580475,"version":"3.54.6"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72231011"],"award-info":[{"award-number":["72231011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133089","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T05:47:23Z","timestamp":1780292843000},"page":"133089","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["A Multi-Objective Collaborative Optimization Framework for Dynamic Multi-Compartment On-Demand Delivery Based on Deep Reinforcement Learning and Evolutionary Search"],"prefix":"10.1016","volume":"331","author":[{"given":"Yicheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingsong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghai","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.eswa.2026.133089_b0005","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1287\/trsc.2023.0252","article-title":"A unified branch-price-and-cut algorithm for multicompartment pickup and delivery problems","volume":"58","author":"Aerts-Veenstra","year":"2024","journal-title":"Transportation Science"},{"issue":"1","key":"10.1016\/j.eswa.2026.133089_b0010","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1287\/trsc.2022.0042","article-title":"Dynamic courier capacity acquisition in rapid delivery systems: A deep q-learning approach","volume":"58","author":"Auad","year":"2024","journal-title":"Transportation Science"},{"issue":"3","key":"10.1016\/j.eswa.2026.133089_b0015","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1287\/msom.2018.0707","article-title":"Coordinating supply and demand on an on-demand service platform with impatient customers","volume":"21","author":"Bai","year":"2019","journal-title":"Manufacturing & Service Operations Management"},{"key":"10.1016\/j.eswa.2026.133089_b0025","doi-asserted-by":"crossref","unstructured":"Chen Y, Qian Y, Yao Y, Wu Z, Li R, et al. (2019b). Can sophisticated dispatching strategy acquired by reinforcement learning?-a case study in dynamic courier dispatching system. arXiv preprint arXiv:1903.02716,.","DOI":"10.65109\/KWHR3408"},{"key":"10.1016\/j.eswa.2026.133089_b0020","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.cor.2019.06.001","article-title":"A multi-compartment vehicle routing problem in cold-chain distribution","volume":"111","author":"Chen","year":"2019","journal-title":"Computers & Operations Research"},{"issue":"2","key":"10.1016\/j.eswa.2026.133089_b0030","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1287\/trsc.2022.1167","article-title":"The pickup and delivery problem with time windows and incompatibility constraints in cold chain transportation","volume":"57","author":"Deng","year":"2023","journal-title":"Transportation Science"},{"key":"10.1016\/j.eswa.2026.133089_b0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.cor.2019.104859","article-title":"Solving the vehicle routing problem with multi-compartment vehicles for city logistics","volume":"115","author":"Eshtehadi","year":"2020","journal-title":"Computers & Operations Research"},{"issue":"2","key":"10.1016\/j.eswa.2026.133089_b0040","first-page":"932","article-title":"Integrated Fleet and Demand Control for On-Demand Meal Delivery Platforms","volume":"72","author":"Hildebrandt","year":"2026","journal-title":"Management Science (INFORMS)"},{"key":"10.1016\/j.eswa.2026.133089_b0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2024.110022","article-title":"Vehicle routing problem for fresh products distribution considering customer satisfaction through adaptive large neighborhood search","volume":"190","author":"Huang","year":"2024","journal-title":"Computers & Industrial Engineering"},{"issue":"1","key":"10.1016\/j.eswa.2026.133089_b0050","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1287\/trsc.2017.0775","article-title":"A multi-compartment vehicle routing problem with loading and unloading costs","volume":"53","author":"H\u00fcbner","year":"2019","journal-title":"Transportation Science"},{"key":"10.1016\/j.eswa.2026.133089_b0055","series-title":"Proceedings of the Genetic and Evolutionary Computation Conference","article-title":"Promoting Two-sided Fairness in Dynamic Vehicle Routing Problems","author":"Kang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133089_b0060","doi-asserted-by":"crossref","unstructured":"Li, M., Qin, Z., Jiao, Y., Yang, Y., Gong, Z., Wang, J., Wang, C., Wu, G., & Ye, J. (2019). Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning. In Proceedings of The Web Conference 2019 (WWW 2019) (pp. 983\u2013994). https:\/\/doi.org\/10.1145\/3308558.3313433.","DOI":"10.1145\/3308558.3313433"},{"key":"10.1016\/j.eswa.2026.133089_b0065","series-title":"Enhancing Dynamic On-demand Food Order Dispatching via Future-informed and Spatial-temporal Extended Decisions","author":"Liang","year":"2023"},{"issue":"2","key":"10.1016\/j.eswa.2026.133089_b0070","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1287\/msom.2022.1171","article-title":"On-demand delivery from stores: Dynamic dispatching and routing with random demand","volume":"25","author":"Liu","year":"2023","journal-title":"Manufacturing & Service Operations Management"},{"key":"10.1016\/j.eswa.2026.133089_b0075","unstructured":"Makhdomi, A. A., & Gillani, I. A. (2025). Predict, Reposition, and Allocate: A Greedy and Flow-Based Architecture for Sustainable Urban Food Delivery. arXiv preprint arXiv:2507.15282. https:\/\/doi.org\/10.48550\/arXiv.2507.15282."},{"issue":"5","key":"10.1016\/j.eswa.2026.133089_b0080","doi-asserted-by":"crossref","first-page":"2535","DOI":"10.1287\/msom.2022.1112","article-title":"On-demand meal delivery platforms: Operational level data and research opportunities","volume":"24","author":"Mao","year":"2022","journal-title":"Manufacturing & Service Operations Management"},{"key":"10.1016\/j.eswa.2026.133089_b0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122488","article-title":"Exploring fairness in food delivery routing and scheduling problems","volume":"240","author":"Mart\u00ednez-Sykora","year":"2024","journal-title":"Expert Systems with Applications"},{"issue":"7540","key":"10.1016\/j.eswa.2026.133089_b0090","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"issue":"2","key":"10.1016\/j.eswa.2026.133089_b0095","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1287\/trsc.2014.0569","article-title":"A methodology based on evolutionary algorithms to solve a dynamic pickup and delivery problem under a hybrid predictive control approach","volume":"49","author":"Mu\u00f1oz-Carpintero","year":"2015","journal-title":"Transportation Science"},{"issue":"4","key":"10.1016\/j.eswa.2026.133089_b0100","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1287\/trsc.2023.0228","article-title":"The dynamic pickup and allocation with fairness problem","volume":"58","author":"Neria","year":"2024","journal-title":"Transportation Science"},{"issue":"1","key":"10.1016\/j.eswa.2026.133089_b0105","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ejor.2012.08.015","article-title":"A review of dynamic vehicle routing problems","volume":"225","author":"Pillac","year":"2013","journal-title":"European Journal of Operational Research"},{"issue":"1","key":"10.1016\/j.eswa.2026.133089_b0110","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/net.21628","article-title":"Dynamic vehicle routing problems: Three decades and counting","volume":"67","author":"Psaraftis","year":"2016","journal-title":"Networks"},{"key":"10.1016\/j.eswa.2026.133089_b0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127818","article-title":"Reinforcement learning-based algorithm for the dynamic multi-depot crowdsourced delivery problem","volume":"283","author":"Ran","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133089_b0120","unstructured":"Schott, J. R. (1995). Fault tolerant design using single and multicriteria genetic algorithm optimization (AFIT-CIA-TR-95-039). http:\/\/hdl.handle.net\/1721.1\/11582."},{"key":"10.1016\/j.eswa.2026.133089_b0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125411","article-title":"A multi-stage competitive swarm optimization algorithm for solving large-scale multi-objective optimization problems","volume":"260","author":"Shang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133089_b0130","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131206","article-title":"A reinforcement learning-driven hyper-heuristic algorithm for haul transportation and terminal delivery optimization in two-echelon distribution systems: A case study in GBA","volume":"309","author":"Tang","year":"2026","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"10.1016\/j.eswa.2026.133089_b0135","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1287\/msom.2017.0678","article-title":"On-demand service platforms","volume":"20","author":"Taylor","year":"2018","journal-title":"Manufacturing & Service Operations Management"},{"key":"10.1016\/j.eswa.2026.133089_b0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.127314","article-title":"Deep reinforcement learning solve the task fairness-oriented flexible pickup and delivery problem","volume":"278","author":"Tian","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"10.1016\/j.eswa.2026.133089_b0145","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1109\/TETCI.2022.3146882","article-title":"Deep reinforcement learning based adaptive operator selection for evolutionary multi-objective optimization","volume":"7","author":"Tian","year":"2022","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"issue":"4","key":"10.1016\/j.eswa.2026.133089_b0150","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1287\/trsc.2019.0958","article-title":"Dynamic pricing and routing for same-day delivery","volume":"54","author":"Ulmer","year":"2020","journal-title":"Transportation Science"},{"key":"10.1016\/j.eswa.2026.133089_b0155","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Deep reinforcement learning with double q-learning","author":"Van Hasselt","year":"2016"},{"key":"10.1016\/j.eswa.2026.133089_b0160","article-title":"A Two-level Reinforcement Learning based Regulation Strategy for Dynamic Operation of O2O Service Ecosystems","volume":"129042","author":"Wang","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133089_b0165","article-title":"Multiobjective vehicle routing optimization with time windows: A hybrid approach using deep reinforcement learning and nsga-ii","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.133089_b0170","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2025.111547","article-title":"A Q-learning based large neighborhood search algorithm for solving food delivery routing problem with uncertain demand and service time","volume":"210","author":"Xiao","year":"2025","journal-title":"Computers & Industrial Engineering"},{"issue":"8","key":"10.1016\/j.eswa.2026.133089_b0175","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1002\/nav.21872","article-title":"Dynamic pricing and matching in ride\u2010hailing platforms","volume":"67","author":"Yan","year":"2020","journal-title":"Naval Research Logistics (NRL)"},{"key":"10.1016\/j.eswa.2026.133089_b0180","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127491","article-title":"Adaptive operator selection with dueling deep Q-network for evolutionary multi-objective optimization","volume":"581","author":"Yin","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.133089_b0185","unstructured":"Zhao, J., Liang, Y., & He, R. (2024). Meituan \u00d7 INFORMS TSL 2024 Research Challenge Dataset. https:\/\/github.com\/meituan\/Meituan-INFORMS-TSL-Research-Challenge."},{"issue":"4","key":"10.1016\/j.eswa.2026.133089_b0190","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/4235.797969","article-title":"Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach","volume":"3","author":"Zitzler","year":"2002","journal-title":"IEEE transactions on Evolutionary Computation"},{"issue":"9","key":"10.1016\/j.eswa.2026.133089_b0195","doi-asserted-by":"crossref","first-page":"9980","DOI":"10.1609\/aaai.v36i9.21236","article-title":"MAPDP: Cooperative multi-agent reinforcement learning to solve pickup and delivery problems","volume":"36","author":"Zong","year":"2022","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426020002?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426020002?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:51:55Z","timestamp":1783147915000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426020002"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":39,"alternative-id":["S0957417426020002"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133089","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A Multi-Objective Collaborative Optimization Framework for Dynamic Multi-Compartment On-Demand Delivery Based on Deep Reinforcement Learning and Evolutionary Search","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133089","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133089"}}