{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:08:27Z","timestamp":1774937307304,"version":"3.50.1"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP180100966"],"award-info":[{"award-number":["DP180100966"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71804034"],"award-info":[{"award-number":["71804034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Committee of Shenzhen","award":["JCYJ20180306171958907"],"award-info":[{"award-number":["JCYJ20180306171958907"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/tcyb.2021.3089179","type":"journal-article","created":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T19:37:25Z","timestamp":1625773045000},"page":"11107-11120","source":"Crossref","is-referenced-by-count":110,"title":["Reinforcement Learning With Multiple Relational Attention for Solving Vehicle Routing Problems"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1721-764X","authenticated-orcid":false,"given":"Yunqiu","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0793-9187","authenticated-orcid":false,"given":"Meng","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Data Mining, Eindhoven University of Technology, Eindhoven, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6468-5729","authenticated-orcid":false,"given":"Ling","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9537-9006","authenticated-orcid":false,"given":"Gangyan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Architecture, Harbin Institute of Technology, Shenzhen, China"}]},{"given":"Yali","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5715-7154","authenticated-orcid":false,"given":"Chengqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611973594","volume-title":"Vehicle Routing: Problems, Methods, and Applications","author":"Toth","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2.4.393"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/opre.45.6.831"},{"key":"ref4","volume-title":"The Traveling Salesman Problem: A Computational Study","author":"Applegate","year":"2007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/0206041"},{"key":"ref6","article-title":"An extension of the Lin-Kernighan-Helsgaun TSP solver for constrained traveling salesman and vehicle routing problems","author":"Helsgaun","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2931434"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2821180"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2962865"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2955599"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950626"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977661"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"ref14","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Vinyals"},{"key":"ref15","volume-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016"},{"key":"ref16","first-page":"9839","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"31","author":"Nazari"},{"key":"ref17","first-page":"1","article-title":"Attention, learn to solve routing problems!","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kool"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Vaswani"},{"key":"ref19","first-page":"1","article-title":"Fast and accurate reading comprehension by combining self-attention and convolution","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref20","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"119","author":"Parisotto"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(92)90192-c"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s43069-021-00101-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/0-306-48056-5_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/003754970107600201"},{"key":"ref25","volume-title":"Google: OR-Tools 7.2","year":"2019"},{"key":"ref26","volume-title":"Gurobi Optimizer Reference Manual","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585892"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.04.163"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/B:ANOR.0000039526.52305.af"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17476"},{"key":"ref31","first-page":"609","article-title":"Reinforcement learning with combinatorial actions: An application to vehicle routing","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Delarue"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/11893028_54"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178938"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.08.026"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17537-4_74"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50039-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-2880-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.04.056"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00339943"},{"key":"ref40","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"27","author":"Sutskever"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3031409"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICPS48405.2020.9274782"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3103811"},{"key":"ref44","volume-title":"Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning","author":"Ma","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207026"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-5577-0_45"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106244"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3009289"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3003163"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93031-2_12"},{"key":"ref51","volume-title":"Learning the multiple traveling salesmen problem with permutation invariant pooling networks","author":"Kaempfer","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231622"},{"key":"ref54","first-page":"6351","article-title":"Learning combinatorial optimization algorithms over graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Dai"},{"key":"ref55","volume-title":"A note on learning algorithms for quadratic assignment with graph neural networks","author":"Nowak","year":"2017"},{"key":"ref56","volume-title":"An efficient graph convolutional network technique for the travelling salesman problem","author":"Joshi","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403356"},{"key":"ref58","volume-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref60","first-page":"12","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Veli\u010dkovi\u0107"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref62","first-page":"6278","article-title":"Learning to perform local rewriting for combinatorial optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Chen"},{"key":"ref63","first-page":"1","article-title":"A learning-based iterative method for solving vehicle routing problems","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lu"},{"key":"ref64","volume-title":"Learning improvement heuristics for solving the travelling salesman problem","author":"Wu","year":"2019"},{"key":"ref65","volume-title":"Learn to design the heuristics for vehicle routing problem","author":"Gao","year":"2020"},{"key":"ref66","first-page":"465","article-title":"Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning","volume-title":"Proc. Asian Conf. Mach. Learn. (ACML)","volume":"129","author":"d. O. da Costa"},{"key":"ref67","first-page":"21188","article-title":"POMO: Policy optimization with multiple optima for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Kwon"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref69","volume-title":"Highway networks","author":"Srivastava","year":"2015"},{"key":"ref70","volume-title":"Towards sparse hierarchical graph classifiers","author":"Cangea","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref73","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"12","author":"Sutton"},{"key":"ref74","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800370304"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1002\/1520-6750(198706)34:3<307::AID-NAV3220340302>3.0.CO;2-D"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.10.2.133"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1002\/net.3230190602"},{"key":"ref79","article-title":"An analysis of the behavior of a class of genetic adaptive systems","author":"De Jong","year":"1975"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0056910"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref83","first-page":"1792","article-title":"Visualizing and understanding Atari agents","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"Greydanus"},{"key":"ref84","first-page":"12329","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Mott"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16916"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3000236"},{"key":"ref87","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Finn"},{"key":"ref88","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Laskin"},{"key":"ref89","first-page":"16495","article-title":"Deep reinforcement learning with stacked hierarchical attention for text-based games","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Xu"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106790"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000364"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1063"},{"key":"ref93","article-title":"DHER: Hindsight experience replay for dynamic goals","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Fang"},{"key":"ref94","article-title":"Curriculum-guided hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Fang"},{"key":"ref95","volume-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9895112\/09478307.pdf?arnumber=9478307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T22:44:41Z","timestamp":1705013081000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9478307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":96,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2021.3089179","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}