{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T13:04:08Z","timestamp":1773061448915,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Alibaba Innovative Research"},{"name":"Center for Intelligent Connected Vehicles and Transportation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tits.2022.3193852","type":"journal-article","created":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T23:32:07Z","timestamp":1659655927000},"page":"24649-24661","source":"Crossref","is-referenced-by-count":20,"title":["Transformer-Based Reinforcement Learning for Pickup and Delivery Problems With Late Penalties"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7397-5560","authenticated-orcid":false,"given":"Ke","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Civil Engineering, Tsinghua University, Beijing, China"}]},{"given":"Xi","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9494-4552","authenticated-orcid":false,"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-016-0454-y"},{"key":"ref31","article-title":"Deep reinforcement learning for solving the heterogeneous capacitated vehicle routing problem","author":"li","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref30","first-page":"7","article-title":"Solving the multi-depot vehicle routing problem using deep reinforcement learning","volume":"2","author":"rintaro","year":"2021","journal-title":"Proc 83rd Nat Conv Inf Process Soc Japan Conf"},{"key":"ref37","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"3840","article-title":"Text compression-aided transformer encoding","volume":"44","author":"li","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101276"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2984033"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.21.4.254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2958859"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2909109"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref14","first-page":"2692","article-title":"Pointer networks","volume":"28","author":"vinyals","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"171","article-title":"Neural combinatorial optimization with reinforcement learning","volume":"6","author":"bello","year":"2016","journal-title":"Math Program Comput"},{"key":"ref16","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","author":"nazari","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"1","article-title":"Attention, learn to solve routing problems!","author":"kool","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3003163"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3056120"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102861"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/net.3230110211"},{"key":"ref27","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2395536"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/17509653.2015.1136247"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106244"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-014-0064-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3141\/1733-01"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107378"},{"key":"ref2","first-page":"2335","article-title":"Solving the pickup and delivery problem with time windows using ‘squeaky wheel’ optimization with local search","author":"lim","year":"2002","journal-title":"Proc Amer Conf Inf Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718515"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012204504849"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2008.02.028"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0548(02)00051-5"},{"key":"ref42","first-page":"57","author":"hansen","year":"2019","journal-title":"Variable Neighbourhood Search"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.1060.0202"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93031-2_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2009.04.012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-004-0173-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5916479"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213003001186"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9972869\/09847118.pdf?arnumber=9847118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:21:10Z","timestamp":1672082470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9847118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2022.3193852","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}