{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:42:43Z","timestamp":1773448963622,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T00:00:00Z","timestamp":1626739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10489-021-02610-0","type":"journal-article","created":{"date-parts":[[2021,7,20]],"date-time":"2021-07-20T16:03:26Z","timestamp":1626797006000},"page":"4274-4299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Order dispatching for an ultra-fast delivery service via deep reinforcement learning"],"prefix":"10.1007","volume":"52","author":[{"given":"Eray Mert","family":"Kavuk","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayse","family":"Tosun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mucahit","family":"Cevik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aysun","family":"Bozanta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sibel B.","family":"Sonu\u00e7","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehmetcan","family":"Tutuncu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bilgin","family":"Kosucu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayse","family":"Basar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,20]]},"reference":[{"key":"2610_CR1","unstructured":"Agarap AF (2018) Deep learning using rectified linear units (relu). CoRR arXiv:1803.08375"},{"key":"2610_CR2","doi-asserted-by":"crossref","unstructured":"Chen B, Qu R, Bai R, Laesanklang W (2019a) A variable neighborhood search algorithm with reinforcement learning for a real-life periodic vehicle routing problem with time windows and open routes. RAIRO Operations Research","DOI":"10.1051\/ro\/2019080"},{"key":"2610_CR3","unstructured":"Chen Y, Qian Y, Yao Y, Wu Z, Li R, Zhou Y, Hu H, Xu Y (2019b) Can sophisticated dispatching strategy acquired by reinforcement learning? In: 18th International Conference on Autonomous Agents and MultiAgent Systems, pp 1395\u20131403"},{"issue":"3","key":"2610_CR4","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1016\/j.ejor.2017.03.060","volume":"262","author":"S Han","year":"2017","unstructured":"Han S, Zhao L, Chen K, Zw Luo, Mishra D (2017) Appointment scheduling and routing optimization of attended home delivery system with random customer behavior. Eur J Oper Res 262(3):966\u2013980","journal-title":"Eur J Oper Res"},{"key":"2610_CR5","doi-asserted-by":"publisher","unstructured":"Holler J, Vuorio R, Qin Z, Tang X, Jiao Y, Jin T, Singh S, Wang C, Ye J (2019) Deep reinforcement learning for multi-driver vehicle dispatching and repositioning problem. In: 2019 IEEE International Conference on Data Mining (ICDM), pp 1090\u20131095. https:\/\/doi.org\/10.1109\/ICDM.2019.00129","DOI":"10.1109\/ICDM.2019.00129"},{"issue":"3","key":"2610_CR6","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1287\/trsc.2018.0861","volume":"53","author":"Y Huang","year":"2019","unstructured":"Huang Y, Zhao L, Powell W B, Tong Y, Ryzhov I O (2019) Optimal learning for urban delivery fleet allocation. Transp Sci 53(3):623\u2013641. https:\/\/doi.org\/10.1287\/trsc.2018.0861","journal-title":"Transp Sci"},{"key":"2610_CR7","unstructured":"Jung J, Jayakrishnan R (2013) Design and modeling of real-time shared-taxi dispatch algorithms. In: Transportation Research Board 92nd Annual Meeting"},{"key":"2610_CR8","unstructured":"Kingma D P, Ba J (2015) Adam: a method for stochastic optimization. CoRR arXiv:1412.6980"},{"key":"2610_CR9","doi-asserted-by":"crossref","unstructured":"Li Y, Zheng Y, Yang Q (2019) Efficient and effective express via contextual cooperative reinforcement learning. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 510\u2013519","DOI":"10.1145\/3292500.3330968"},{"issue":"15","key":"2610_CR10","doi-asserted-by":"publisher","first-page":"6917","DOI":"10.1016\/j.eswa.2014.04.036","volume":"41","author":"C Lin","year":"2014","unstructured":"Lin C, Choy K L, Ho G T, Lam H, Pang G K, Chin K S (2014) A decision support system for optimizing dynamic courier routing operations. Expert Syst Appl 41(15):6917\u20136933","journal-title":"Expert Syst Appl"},{"key":"2610_CR11","doi-asserted-by":"publisher","unstructured":"Lin K, Zhao R, Xu Z, Zhou J (2018) Efficient large-scale fleet management via multi-agent deep reinforcement learning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD\u201918. Association for Computing Machinery, New York, pp 1774\u20131783. https:\/\/doi.org\/10.1145\/3219819.3219993","DOI":"10.1145\/3219819.3219993"},{"key":"2610_CR12","unstructured":"Lu Z, Pu H, Wang F, Hu Z, Wang L (2017) The expressive power of neural networks: a view from the width. In: Guyon I, Luxburg U V, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol 30, Curran Associates, Inc., pp 6231\u20136239"},{"issue":"6","key":"2610_CR13","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1109\/TNNLS.2018.2790388","volume":"29","author":"M Mahmud","year":"2018","unstructured":"Mahmud M, Kaiser MS, Hussain A, Vassanelli S (2018) Applications of deep learning and reinforcement learning to biological data. IEEE Trans Neural Netw Learn Syst 29(6):2063\u20132079. https:\/\/doi.org\/10.1109\/TNNLS.2018.2790388","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2610_CR14","doi-asserted-by":"publisher","unstructured":"Masoud N, Jayakrishnan R (2017) A real-time algorithm to solve the peer-to-peer ride-matching problem in a flexible ridesharing system. Transportation Research Part B Methodological. https:\/\/doi.org\/10.1016\/j.trb.2017.10.006","DOI":"10.1016\/j.trb.2017.10.006"},{"issue":"253","key":"2610_CR15","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","volume":"46","author":"FJ Massey Jr","year":"1951","unstructured":"Massey Jr FJ (1951) The kolmogorov-smirnov test for goodness of fit. J Am Stat Assoc 46 (253):68\u201378. https:\/\/doi.org\/10.1080\/01621459.1951.10500769","journal-title":"J Am Stat Assoc"},{"key":"2610_CR16","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. In: NIPS Deep Learning Workshop"},{"key":"2610_CR17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu A A, Veness J, Bellemare M G, Graves A, Riedmiller M, Fidjeland A K, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533","journal-title":"Nature"},{"key":"2610_CR18","doi-asserted-by":"crossref","unstructured":"Ota M, Vo H, Silva C, Freire J (2015) A scalable approach for data-driven taxi ride-sharing simulation. In: 2015 IEEE International Conference on Big Data (Big Data), pp 888\u2013897","DOI":"10.1109\/BigData.2015.7363837"},{"key":"2610_CR19","unstructured":"Pitel L (2020) Michael moritz backs turkish grocery start-up. Available from https:\/\/www.ft.com\/content\/d0a427f6-36e0-11ea-a6d3-9a26f8c3cba4"},{"issue":"5","key":"2610_CR20","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1287\/inte.2020.1047","volume":"50","author":"Z Qin","year":"2020","unstructured":"Qin Z, Tang X, Jiao Y, Zhang F, Xu Z, Zhu H, Ye J (2020) Ride-hailing order dispatching at didi via reinforcement learning. INFORMS J Appl Anal 50(5):272\u2013286","journal-title":"INFORMS J Appl Anal"},{"issue":"4","key":"2610_CR21","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1287\/trsc.2018.0857","volume":"53","author":"MI Restrepo","year":"2019","unstructured":"Restrepo M I, Semet F, Pocreau T (2019) Integrated shift scheduling and load assignment optimization for attended home delivery. Transp Sci 53(4):1150\u20131174","journal-title":"Transp Sci"},{"key":"2610_CR22","unstructured":"Reyes D, Erera A L, Savelsbergh M W P, Sahasrabudhe S, O\u2019Neil RJ (2018) The meal delivery routing problem. Technical Report"},{"key":"2610_CR23","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2016) Prioritized experience replay. In: International Conference on Learning Representations"},{"issue":"7587","key":"2610_CR24","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison C J, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T, Hassabis D (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484\u2013489. https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"issue":"2","key":"2610_CR25","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1287\/trsc.1090.0303","volume":"44","author":"I Sungur","year":"2010","unstructured":"Sungur I, Ren Y, Ordonez F, Dessouky M, Zhong H (2010) A model and algorithm for the courier delivery problem with uncertainty. Transp Sci 44(2):193\u2013205. https:\/\/doi.org\/10.1287\/trsc.1090.0303","journal-title":"Transp Sci"},{"key":"2610_CR26","unstructured":"Sutton RS, Barto AG (2018) Reinforcement Learning: An Introduction, 2nd edn. The MIT Press"},{"issue":"6","key":"2610_CR27","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1109\/TCYB.2019.2904742","volume":"50","author":"T Tan","year":"2020","unstructured":"Tan T, Bao F, Deng Y, Jin A, Dai Q, Wang J (2020) Cooperative deep reinforcement learning for large-scale traffic grid signal control. IEEE Trans Cybern 50(6):2687\u20132700. https:\/\/doi.org\/10.1109\/TCYB.2019.2904742","journal-title":"IEEE Trans Cybern"},{"key":"2610_CR28","doi-asserted-by":"publisher","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. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD \u201919, Association for Computing Machinery, New York, p 1780\u20131790. https:\/\/doi.org\/10.1145\/3292500.3330724","DOI":"10.1145\/3292500.3330724"},{"key":"2610_CR29","doi-asserted-by":"publisher","unstructured":"Ulmer MW, Thomas BW, Mattfeld DC (2019) Preemptive depot returns for dynamic same-day delivery. EURO J Transp Logist 8(4):327\u2013361. https:\/\/doi.org\/10.1007\/s13676-018-0124-0, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2192437620300479","DOI":"10.1007\/s13676-018-0124-0"},{"issue":"4","key":"2610_CR30","doi-asserted-by":"publisher","first-page":"321","DOI":"10.9746\/jcmsi.11.321","volume":"11","author":"F Uwano","year":"2018","unstructured":"Uwano F, TATEBE N, TAJIMA Y, NAKATA M, KOVACS T, TAKADAMA K (2018) Multi-agent cooperation based on reinforcement learning with internal reward in maze problem. SICE J Control Measur Syst Integr 11(4):321\u2013330. https:\/\/doi.org\/10.9746\/jcmsi.11.321","journal-title":"SICE J Control Measur Syst Integr"},{"key":"2610_CR31","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 30","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"2610_CR32","doi-asserted-by":"crossref","unstructured":"Vera JM, Abad AG (2019) Deep reinforcement learning for routing a heterogeneous fleet of vehicles. In: 2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI), pp 1\u20136","DOI":"10.1109\/LA-CCI47412.2019.9037042"},{"key":"2610_CR33","unstructured":"Wang Z, Schaul T, Hessel M, Hasselt H, Lanctot M, Freitas N (2016) Dueling network architectures for deep reinforcement learning. In: Balcan MF, Weinberger KQ (eds) Proceedings of The 33rd International Conference on Machine Learning, PMLR, vol 48. Proceedings of Machine Learning Research, New York, pp 1995\u20132003. http:\/\/proceedings.mlr.press\/v48\/wangf16.html"},{"key":"2610_CR34","doi-asserted-by":"publisher","unstructured":"Wang Z, Qin Z, Tang X, Ye J, Zhu H (2018) Deep reinforcement learning with knowledge transfer for online rides order dispatching. In: 2018 IEEE International Conference on Data Mining (ICDM), pp 617\u2013626, https:\/\/doi.org\/10.1109\/ICDM.2018.00077","DOI":"10.1109\/ICDM.2018.00077"},{"key":"2610_CR35","doi-asserted-by":"publisher","unstructured":"Zhao J, Mao M, Zhao X, Zou J (2020) A hybrid of deep reinforcement learning and local search for the vehicle routing problems. IEEE Trans Intell Transp Syst:1\u201311. https:\/\/doi.org\/10.1109\/TITS.2020.3003163","DOI":"10.1109\/TITS.2020.3003163"},{"key":"2610_CR36","doi-asserted-by":"publisher","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. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM \u201919. Association for Computing Machinery, New York, pp 2645\u20132653. https:\/\/doi.org\/10.1145\/3357384.3357799","DOI":"10.1145\/3357384.3357799"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02610-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02610-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02610-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:23:13Z","timestamp":1672878193000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02610-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,20]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["2610"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02610-0","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,20]]},"assertion":[{"value":"11 June 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}