{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T22:20:53Z","timestamp":1783117253144,"version":"3.54.6"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC-114-2224-E-027-001"],"award-info":[{"award-number":["NSTC-114-2224-E-027-001"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004386","name":"Universiti Malaya","doi-asserted-by":"publisher","award":["MGIF008-2026"],"award-info":[{"award-number":["MGIF008-2026"]}],"id":[{"id":"10.13039\/501100004386","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004386","name":"Universiti Malaya","doi-asserted-by":"publisher","award":["IF014-2026"],"award-info":[{"award-number":["IF014-2026"]}],"id":[{"id":"10.13039\/501100004386","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.ins.2026.123671","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T23:27:55Z","timestamp":1779492475000},"page":"123671","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A transductive learning-based method for vehicle routing problems using off-policy proximal policy optimization and hyperparameter optimization"],"prefix":"10.1016","volume":"754","author":[{"given":"Xiaobo","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0793-3308","authenticated-orcid":false,"given":"Chin Soon","family":"Ku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0898-5054","authenticated-orcid":false,"given":"Roohallah","family":"Alizadehsani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4317-2801","authenticated-orcid":false,"given":"Pawe\u0142","family":"P\u0142awiak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9675-5819","authenticated-orcid":false,"given":"Ryszard","family":"Tadeusiewicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4278-8740","authenticated-orcid":false,"given":"Qi","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uzair Aslam","family":"Bhatti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5865-1533","authenticated-orcid":false,"given":"Lip Yee","family":"Por","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2026.123671_b0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.sftr.2024.100390","article-title":"Scientific mapping and research perspectives of the vehicle routing problem: an approach from sustainability strategies","volume":"8","author":"Alzate","year":"2024","journal-title":"Sustain Futures"},{"key":"10.1016\/j.ins.2026.123671_b0010","doi-asserted-by":"crossref","first-page":"7394","DOI":"10.3390\/su15097394","article-title":"A bibliometric visualized analysis and classification of vehicle routing problem research","volume":"15","author":"Ni","year":"2023","journal-title":"Sustainability"},{"key":"10.1016\/j.ins.2026.123671_b0015","doi-asserted-by":"crossref","first-page":"124","DOI":"10.3390\/sym15010124","article-title":"A genetic algorithm for the waitable time-varying multi-depot green vehicle routing problem","volume":"15","author":"Chen","year":"2023","journal-title":"Symmetry (basel)"},{"key":"10.1016\/j.ins.2026.123671_b0020","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","article-title":"Machine learning for combinatorial optimization: a methodological tour d\u2019horizon","volume":"290","author":"Bengio","year":"2021","journal-title":"Eur. J. Oper. Res."},{"key":"10.1016\/j.ins.2026.123671_b0025","series-title":"In: Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","first-page":"236","article-title":"Deep reinforcement learning algorithm for fast solutions to vehicle routing problem with time-windows","author":"Gupta","year":"2022"},{"key":"10.1016\/j.ins.2026.123671_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.rineng.2026.110517","article-title":"Comparative analysis of metaheuristic techniques for Logistics 4.0 optimization: Dynamic vehicle routing and LSTM hyperparameter tuning","author":"Hmamou","year":"2026","journal-title":"Results Eng."},{"key":"10.1016\/j.ins.2026.123671_b0035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2019.12.030","article-title":"Transductive LSTM for time-series prediction: an application to weather forecasting","volume":"125","author":"Karevan","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.ins.2026.123671_b0040","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1007\/s10489-022-03456-w","article-title":"Deep reinforcement learning for the dynamic and uncertain vehicle routing problem","volume":"53","author":"Pan","year":"2023","journal-title":"Appl. Intell."},{"key":"10.1016\/j.ins.2026.123671_b0045","doi-asserted-by":"crossref","unstructured":"Raza, S.M., Sajid, M., Singh, J., Vehicle routing problem using reinforcement learning: recent advancements, in: Advanced Machine Intelligence and Signal Processing, Springer Nature Singapore, Singapore, 2022, pp. 269\u2013280. https:\/\/doi.org\/10.1007\/978-981-19-0840-8_20.","DOI":"10.1007\/978-981-19-0840-8_20"},{"key":"10.1016\/j.ins.2026.123671_b0050","doi-asserted-by":"crossref","first-page":"33671","DOI":"10.1109\/JIOT.2024.3432911","article-title":"An end-to-end deep reinforcement learning framework for electric vehicle routing problem","volume":"11","author":"Wang","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.ins.2026.123671_b0055","doi-asserted-by":"crossref","first-page":"4779","DOI":"10.1109\/TNNLS.2024.3371781","article-title":"Deep reinforcement learning for solving vehicle routing problems with backhauls","volume":"36","author":"Wang","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10.1016\/j.ins.2026.123671_b0060","article-title":"Deep reinforcement learning for dynamic vehicle routing with demand and traffic uncertainty","author":"Kadyrov","year":"2025","journal-title":"Oper. Res. Perspect."},{"key":"10.1016\/j.ins.2026.123671_b0065","doi-asserted-by":"crossref","first-page":"6497","DOI":"10.1007\/s13369-025-10744-3","article-title":"Reinforcement learning for the vehicle routing problem: Methodologies, applications, and research outlook","volume":"51","author":"Liu","year":"2026","journal-title":"Arab. J. Sci. Eng."},{"key":"10.1016\/j.ins.2026.123671_b0070","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.3390\/app15031068","article-title":"A reinforcement learning-based solution for the capacitated electric vehicle routing problem from the last-mile delivery perspective","volume":"15","author":"Aslan Y\u0131ld\u0131z","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.ins.2026.123671_b0075","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.ins.2026.123671_b0080","doi-asserted-by":"crossref","first-page":"349","DOI":"10.3390\/pr11020349","article-title":"Hyperparameter search for machine learning algorithms for optimizing the computational complexity","volume":"11","author":"Ali","year":"2023","journal-title":"Processes"},{"key":"10.1016\/j.ins.2026.123671_b0085","doi-asserted-by":"crossref","first-page":"3866","DOI":"10.1016\/j.procs.2023.10.382","article-title":"An improved genetic algorithm for solving the multi-objective vehicle routing problem with environmental considerations","volume":"225","author":"Labidi","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.ins.2026.123671_b0090","article-title":"Metade: Evolving differential evolution by differential evolution","author":"Chen","year":"2025","journal-title":"IEEE Trans. Evol. Comput."},{"key":"10.1016\/j.ins.2026.123671_b0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2024.112517","article-title":"Adaptive constrained multi-objective differential evolution algorithm for vehicle routing problem considering crowdsourcing delivery","volume":"169","author":"Hou","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.ins.2026.123671_b0100","doi-asserted-by":"crossref","first-page":"91","DOI":"10.4995\/ijpme.2024.19928","article-title":"An adaptive differential evolution algorithm to solve the multi-compartment vehicle routing problem: a case of cold chain transportation problem","volume":"12","author":"Sankul","year":"2024","journal-title":"Int J Prod Manag Eng"},{"key":"10.1016\/j.ins.2026.123671_b0105","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.ejor.2023.01.017","article-title":"A general deep reinforcement learning hyperheuristic framework for solving combinatorial optimization problems","volume":"309","author":"Kallestad","year":"2023","journal-title":"Eur. J. Oper. Res."},{"key":"10.1016\/j.ins.2026.123671_b0110","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1016\/j.ins.2022.11.073","article-title":"Solving combinatorial optimization problems over graphs with BERT-based deep reinforcement learning","volume":"619","author":"Wang","year":"2023","journal-title":"Inf Sci (n Y)"},{"key":"10.1016\/j.ins.2026.123671_b0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119789","article-title":"An optimization model for vehicle routing problem in last-mile delivery","volume":"222","author":"Tiwari","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123671_b0120","first-page":"4191","article-title":"SoC-VRP: a deep-reinforcement-learning-based vehicle route planning mechanism for service-oriented cooperative ITS","volume":"12","author":"Hou","year":"2023","journal-title":"Electronics (basel)"},{"key":"10.1016\/j.ins.2026.123671_b0125","doi-asserted-by":"crossref","unstructured":"D.H. Lee, J. Ahn, A Deep reinforcement learning approach to solve the vehicle routing problem with resource constraints, in: AIAA SCITECH 2023 Forum, American Institute of Aeronautics and Astronautics, 2023. https:\/\/doi.org\/10.2514\/6.2023-2662.","DOI":"10.2514\/6.2023-2662"},{"key":"10.1016\/j.ins.2026.123671_b0130","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence 35","first-page":"12042","article-title":"Multi-decoder attention model with embedding glimpse for solving vehicle routing problems","author":"Xin","year":"2021"},{"key":"10.1016\/j.ins.2026.123671_b0135","doi-asserted-by":"crossref","first-page":"11107","DOI":"10.1109\/TCYB.2021.3089179","article-title":"Reinforcement learning with multiple relational attention for solving vehicle routing problems","volume":"52","author":"Xu","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.ins.2026.123671_b0140","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.neucom.2022.08.005","article-title":"Solve routing problems with a residual edge-graph attention neural network","volume":"508","author":"Lei","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ins.2026.123671_b0145","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.neunet.2023.05.003","article-title":"An accelerated end-to-end method for solving routing problems","volume":"164","author":"Zhu","year":"2023","journal-title":"Neural Netw."},{"key":"10.1016\/j.ins.2026.123671_b0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.jksuci.2023.101787","article-title":"Generative inverse reinforcement learning for learning 2-opt heuristics without extrinsic rewards in routing problems","volume":"35","author":"Wang","year":"2023","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"10.1016\/j.ins.2026.123671_b0155","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118812","article-title":"A reinforcement learning-variable neighborhood search method for the capacitated vehicle routing problem","volume":"213","author":"Kalatzantonakis","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123671_b0160","doi-asserted-by":"crossref","unstructured":"Y. Jiang, Z. Cao, Y. Wu, W. Song, J. Zhang, Ensemble-based deep reinforcement learning for vehicle routing problems under distribution shift, in: A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, S. Levine (Eds.), Adv Neural Inf Process Syst, Curran Associates, Inc., 2023: pp. 53112\u201353125. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/a68120d2eb2f53f7d9e71547591aef11-Paper-Conference.pdf.","DOI":"10.52202\/075280-2311"},{"key":"10.1016\/j.ins.2026.123671_b0165","unstructured":"F. Berto, C. Hua, N.G. Zepeda, A. Hottung, N. Wouda, L. Lan, J. Park, K. Tierney, J. Park, RouteFinder: Towards foundation models for vehicle routing problems, ArXiv (Preprint) (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.15007."},{"key":"10.1016\/j.ins.2026.123671_b0170","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1109\/JAS.2022.105677","article-title":"An overview and experimental study of learning-based optimization algorithms for the vehicle routing problem","volume":"9","author":"Li","year":"2022","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.ins.2026.123671_b0175","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1080\/00207543.2021.2013566","article-title":"Analytics and machine learning in vehicle routing research","volume":"61","author":"Bai","year":"2023","journal-title":"Int. J. Prod. Res."},{"key":"10.1016\/j.ins.2026.123671_b0180","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s10732-025-09568-z","article-title":"A random-key optimizer for combinatorial optimization","volume":"31","author":"Chaves","year":"2025","journal-title":"J. Heuristics"},{"key":"10.1016\/j.ins.2026.123671_b0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126196","article-title":"Transportation mode detection through spatial attention-based transductive long short-term memory and off-policy feature selection","volume":"267","author":"Merikhipour","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.ins.2026.123671_b0190","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1002\/tee.23771","article-title":"Graph transformer with reinforcement learning for vehicle routing problem","volume":"18","author":"Fellek","year":"2023","journal-title":"IEEJ Transactions on Electrical and Electronic Engineering"},{"key":"10.1016\/j.ins.2026.123671_b0195","unstructured":"T. Cuvelier, F. Didier, V. Furnon, S. Gay, S. Mohajeri, L. Perron, OR-Tools\u2019 Vehicle Routing Solver: a Generic Constraint-Programming Solver with Heuristic Search for Routing Problems, in: 24e Congr\u00e8s Annuel de La Soci\u00e9t\u00e9 Fran\u00e7aise de Recherche Op\u00e9rationnelle et d\u2019aide \u00e0 La D\u00e9cision, ROADEF, Rennes, France, 2023: pp. 1\u20132. https:\/\/hal.science\/hal-04015496v1\/file\/ROADEF_2023_ORTools.pdf."},{"key":"10.1016\/j.ins.2026.123671_b0200","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1287\/opre.35.2.254","article-title":"Algorithms for the Vehicle Routing and Scheduling Problems with Time Window Constraints","volume":"35","author":"Solomon","year":"1987","journal-title":"Oper. Res."}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S002002552600602X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S002002552600602X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T21:38:20Z","timestamp":1783114700000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S002002552600602X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":40,"alternative-id":["S002002552600602X"],"URL":"https:\/\/doi.org\/10.1016\/j.ins.2026.123671","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A transductive learning-based method for vehicle routing problems using off-policy proximal policy optimization and hyperparameter optimization","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ins.2026.123671","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"123671"}}