{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T13:07:37Z","timestamp":1769260057913,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"BNRist Project","award":["BNR2024TD03003"],"award-info":[{"award-number":["BNR2024TD03003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936009"],"award-info":[{"award-number":["61936009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research and Development Project of CRSC Research & Design Institute Group Company, Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tetci.2025.3581113","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:40:03Z","timestamp":1751290803000},"page":"425-439","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning for Traveling Purchaser Problems"],"prefix":"10.1109","volume":"10","author":[{"given":"Haofeng","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Automation & BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7266-8603","authenticated-orcid":false,"given":"Rongping","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Automation & BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1571-3241","authenticated-orcid":false,"given":"Wanlu","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation & BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-9283","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Automation & BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4355-5340","authenticated-orcid":false,"given":"Keyou","family":"You","sequence":"additional","affiliation":[{"name":"Department of Automation & BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7850-0377","authenticated-orcid":false,"given":"Wei","family":"Fan","sequence":"additional","affiliation":[{"name":"AI Laboratory, Lenovo Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1966.56"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2008.10.027"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2015.0627"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.08.039"},{"issue":"2","key":"ref5","first-page":"78","article-title":"Travelling purchaser problem","volume":"18","author":"Ramesh","year":"1981","journal-title":"Opsearch"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2016.12.017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/opre.51.6.940.24921"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-006-0014-y"},{"key":"ref9","article-title":"TPPLIB","volume-title":"ull.es.","author":"Riera-Ledesma","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0305-0483(81)90087-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(82)90041-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0548(98)00032-X"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3146882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17430"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3402685"},{"key":"ref17","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vinyals","year":"2015"},{"key":"ref18","article-title":"Neural combinatorial optimization with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bello","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105905"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236629"},{"key":"ref21","first-page":"9861","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nazari","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102861"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3139802"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3444698"},{"key":"ref25","article-title":"Attention, learn to solve routing problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kool","year":"2019"},{"key":"ref26","article-title":"An efficient graph convolutional network technique for the travelling salesman problem","author":"Joshi","year":"2019"},{"key":"ref27","first-page":"21188","article-title":"POMO: Policy optimization with multiple optima for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kwon","year":"2020"},{"key":"ref28","first-page":"1936","article-title":"Sym-NCO: Leveraging symmetricity for neural combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2022"},{"key":"ref29","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"ref31","article-title":"Solving mixed integer programs using neural networks","author":"Nair","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2021.1045"},{"key":"ref33","article-title":"On representing mixed-integer linear programs by graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref35","article-title":"How powerful are graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10601-022-09327-y"},{"key":"ref37","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref44","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/11361307\/11059335.pdf?arnumber=11059335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T21:01:23Z","timestamp":1769202083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11059335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2025.3581113","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}