{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:13:15Z","timestamp":1774296795750,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:00:00Z","timestamp":1631836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71771035"],"award-info":[{"award-number":["71771035"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71831003"],"award-info":[{"award-number":["71831003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s10489-021-02750-3","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T00:21:47Z","timestamp":1631838107000},"page":"6853-6865","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Online food ordering delivery strategies based on deep reinforcement learning"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1890-6874","authenticated-orcid":false,"given":"Guangyu","family":"Zou","sequence":"first","affiliation":[]},{"given":"Jiafu","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Levent","family":"Yilmaz","sequence":"additional","affiliation":[]},{"given":"Xiangyu","family":"Kong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,17]]},"reference":[{"key":"2750_CR1","doi-asserted-by":"publisher","first-page":"105728","DOI":"10.1016\/j.asoc.2019.105728","volume":"84","author":"AM Altabeeb","year":"2019","unstructured":"Altabeeb AM, Mohsen AM, Ghallab A (2019) An improved hybrid firefly algorithm for capacitated vehicle routing problem. Appl Soft Comput 84:105728","journal-title":"Appl Soft Comput"},{"key":"2750_CR2","unstructured":"Behrisch M, Bieker L, Erdmann J, Krajzewicz D (2011) Sumo - simulation of urban mobility: An overview. In: The third international conference on advances in system simulation"},{"key":"2750_CR3","doi-asserted-by":"publisher","first-page":"1699","DOI":"10.1007\/s10994-019-05849-4","volume":"109","author":"S-A Chen","year":"2020","unstructured":"Chen S-A, Tangkaratt V, Lin H-T, Sugiyama M (2020) Active deep q-learning with demonstration. Mach Learn 109:1699\u20131725","journal-title":"Mach Learn"},{"key":"2750_CR4","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.tre.2018.01.004","volume":"111","author":"DG Mogale","year":"2019","unstructured":"Mogale DG, Mukesh KS, Krishna K, Manoj KT (2019) Grain silo location-allocation problem with dwell time for optimization of food grain supply chain network. Transp Res Part E Logist Transp Rev 111:40\u201369","journal-title":"Transp Res Part E Logist Transp Rev"},{"key":"2750_CR5","doi-asserted-by":"crossref","unstructured":"Elmachtoub AN, Grigas P (2021) Smart \u201cpredict, then optimize\u201d. Manag Sci","DOI":"10.1287\/mnsc.2020.3922"},{"key":"2750_CR6","doi-asserted-by":"publisher","first-page":"106242","DOI":"10.1016\/j.cie.2019.106242","volume":"140","author":"R Elshaer","year":"2020","unstructured":"Elshaer R, Awad H (2020) A taxonomic review of metaheuristic algorithms for solving the vehicle routing problem and its variants. Comput Ind Eng 140:106242","journal-title":"Comput Ind Eng"},{"issue":"1","key":"2750_CR7","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1287\/msom.2015.0561","volume":"18","author":"KJ Ferreira","year":"2016","unstructured":"Ferreira KJ, Lee BHA, Simchi-Levi D (2016) Analytics for an online retailer: Demand forecasting and price optimization. Manuf Serv Oper Manag 18(1):69\u201388","journal-title":"Manuf Serv Oper Manag"},{"key":"2750_CR8","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.jocs.2017.12.012","volume":"25","author":"R Goel","year":"2018","unstructured":"Goel R, Maini R (2018) A hybrid of ant colony and firefly algorithms (hafa) for solving vehicle routing problems. J Comput Sci 25:28\u201337","journal-title":"J Comput Sci"},{"key":"2750_CR9","first-page":"2613","volume":"23","author":"H Hado","year":"2010","unstructured":"Hado H (2010) Double q-learning. Adv Neural Inf Process Syst 23:2613\u20132621","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"2750_CR10","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1287\/trsc.2016.0682","volume":"52","author":"MA Klapp","year":"2018","unstructured":"Klapp MA, Erera AL, Toriello A (2018) The one-dimensional dynamic dispatch waves problem. Transp Sci 52(2):402\u2013415","journal-title":"Transp Sci"},{"issue":"1","key":"2750_CR11","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s10489-020-01786-1","volume":"51","author":"C Li","year":"2021","unstructured":"Li C, Li Y, Zhao Y, Peng P, Sler XG (2021) Self-generated long-term experience replay for continual reinforcement learning. Appl Intell 51(1):185\u2013201","journal-title":"Appl Intell"},{"key":"2750_CR12","doi-asserted-by":"publisher","first-page":"146707","DOI":"10.1109\/ACCESS.2020.3014638","volume":"8","author":"H Li","year":"2020","unstructured":"Li H, Li Z, Li C, Wang R, Mu R (2020) Research on optimization of electric vehicle routing problem with time window. IEEE Access 8:146707\u2013146718","journal-title":"IEEE Access"},{"key":"2750_CR13","doi-asserted-by":"crossref","unstructured":"Li M, Qin Z, Jiao Y, Yang Y, Wang J, Wang C, Guobin W, Ye J (2019) Efficient ridesharing order dispatching with mean field multi-agent reinforcement learning. In: The world wide web conference, pp 983\u2013994","DOI":"10.1145\/3308558.3313433"},{"key":"2750_CR14","doi-asserted-by":"crossref","unstructured":"Liu S, He L, Max Shen Z-J (2020) On-time last-mile delivery: Order assignment with travel-time predictors. Manag Sci","DOI":"10.1287\/mnsc.2020.3741"},{"key":"2750_CR15","doi-asserted-by":"crossref","unstructured":"Lopez PA, Behrisch M, Bieker-Walz L, Erdmann J, Fl\u00f6tter\u00f6d Y-P, Hilbrich R, L\u00fccken L., Rummel J, Wagner P, Wie\u00dfner E. (2018) Microscopic traffic simulation using sumo. In: The 21st IEEE international conference on intelligent transportation systems. IEEE","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"2750_CR16","doi-asserted-by":"publisher","first-page":"102626","DOI":"10.1016\/j.trc.2020.102626","volume":"115","author":"C Mao","year":"2020","unstructured":"Mao C, Liu Y, Shen Z-JM (2020) Dispatch of autonomous vehicles for taxi services: A deep reinforcement learning approach. Trans Res Part C Emerg Technol 115:102626","journal-title":"Trans Res Part C Emerg Technol"},{"key":"2750_CR17","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.ins.2018.12.086","volume":"481","author":"Y Marinakis","year":"2019","unstructured":"Marinakis Y, Marinaki M, Migdalas A (2019) A multi-adaptive particle swarm optimization for the vehicle routing problem with time windows. Inform Sci 481:311\u2013329","journal-title":"Inform Sci"},{"key":"2750_CR18","doi-asserted-by":"publisher","first-page":"125141","DOI":"10.1016\/j.jclepro.2020.125141","volume":"289","author":"YZ Mehrjerdi","year":"2021","unstructured":"Mehrjerdi YZ, Shafiee M (2021) A resilient and sustainable closed-loop supply chain using multiple sourcing and information sharing strategies. J Clean Prod 289:125141","journal-title":"J Clean Prod"},{"key":"2750_CR19","unstructured":"meituan.com (2019) The research report for the industry of food delivery service in China 2019. https:\/\/mri.meituan.com\/institute"},{"issue":"6","key":"2750_CR20","doi-asserted-by":"publisher","first-page":"2227","DOI":"10.1109\/TNNLS.2018.2806087","volume":"29","author":"J Pan","year":"2018","unstructured":"Pan J, Wang X, Cheng Y, Qiang Y (2018) Multisource transfer double dqn based on actor learning. IEEE Trans Neural Netw Learn Syst 29(6):2227\u20132238","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2750_CR21","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.procs.2019.01.104","volume":"149","author":"D Plinere","year":"2019","unstructured":"Plinere D, Aleksejeva L (2019) Production scheduling in agent-based supply chain for manufacturing efficiency improvement. Procedia Comput Sci 149:36\u201343","journal-title":"Procedia Comput Sci"},{"key":"2750_CR22","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.cor.2018.07.021","volume":"100","author":"M Qiu","year":"2018","unstructured":"Qiu M, Zhuo F, Eglese R, Tang Q (2018) A tabu search algorithm for the vehicle routing problem with discrete split deliveries and pickups. Comput Oper Res 100:102\u2013116","journal-title":"Comput Oper Res"},{"key":"2750_CR23","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.cie.2019.05.002","volume":"133","author":"E Ruiz","year":"2019","unstructured":"Ruiz E, Soto-Mendoza V, Barbosa AER, Reyes R (2019) Solving the open vehicle routing problem with capacity and distance constraints with a biased random key genetic algorithm. Comput Ind Eng 133:207\u2013219","journal-title":"Comput Ind Eng"},{"key":"2750_CR24","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1016\/j.jag.2018.02.012","volume":"68","author":"S Saeedi","year":"2018","unstructured":"Saeedi S (2018) Integrating macro and micro scale approaches in the agent-based modeling of residential dynamics. Int J Appl Earth Obs Geoinf 68:214\u2013229","journal-title":"Int J Appl Earth Obs Geoinf"},{"issue":"1","key":"2750_CR25","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.ejor.2019.02.025","volume":"277","author":"A Marques","year":"2019","unstructured":"Ricardo S., Marques A, Amorim P, Rasinm\u00e4ki J. (2019) Multiple vehicle synchronisation in a full truck-load pickup and delivery problem: A case-study in the biomass supply chain. Eur J Oper Res 277 (1):174\u2013194","journal-title":"Eur J Oper Res"},{"issue":"3","key":"2750_CR26","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1111\/j.1540-5915.1998.tb01356.x","volume":"29","author":"JM Swaminathan","year":"2007","unstructured":"Swaminathan JM, Smith SF, Sadeh NM (2007) Modeling supply chain dynamics: A multiagent approach. Decis Sci 29(3):607\u2013632","journal-title":"Decis Sci"},{"key":"2750_CR27","doi-asserted-by":"crossref","unstructured":"Hasselt HV, 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"},{"issue":"3-4","key":"2750_CR28","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8(3-4):279\u2013292","journal-title":"Mach Learn"},{"issue":"2","key":"2750_CR29","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s10489-018-1296-x","volume":"49","author":"X Zhao","year":"2019","unstructured":"Zhao X, Ding S, An Y, Jia W (2019) Applications of asynchronous deep reinforcement learning based on dynamic updating weights. Appl Intell 49(2):581\u2013591","journal-title":"Appl Intell"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02750-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02750-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02750-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T12:34:54Z","timestamp":1673267694000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02750-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,17]]},"references-count":29,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["2750"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02750-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,17]]},"assertion":[{"value":"5 August 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 September 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}