{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:33:54Z","timestamp":1774370034781,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100015665","name":"Grantham Centre for Sustainable Futures","doi-asserted-by":"publisher","award":["X\/008802-16-60"],"award-info":[{"award-number":["X\/008802-16-60"]}],"id":[{"id":"10.13039\/100015665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3505678","type":"journal-article","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T18:49:07Z","timestamp":1732560547000},"page":"181477-181497","source":"Crossref","is-referenced-by-count":4,"title":["Leveraging Transfer Learning in Deep Reinforcement Learning for Solving Combinatorial Optimization Problems Under Uncertainty"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9918-4820","authenticated-orcid":false,"given":"Fatima","family":"Ezzahra Achamrah","sequence":"first","affiliation":[{"name":"Sheffield University Management School, The University of Sheffield, Sheffield, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2022.106071"},{"key":"ref4","article-title":"Neural combinatorial optimization with reinforcement learning","author":"Bello","year":"2016","journal-title":"arXiv:1611.09940"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103981"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3111082"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2023.0107"},{"key":"ref8","first-page":"1","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nazari"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2024.103415"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1987549"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.10.049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2240433"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2495145"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1057\/s41272-021-00285-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987820"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01847-3"},{"key":"ref17","article-title":"RL4CO: An extensive reinforcement learning for combinatorial optimization benchmark","author":"Berto","year":"2023","journal-title":"arXiv:2306.17100"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2017.09.110"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref22","article-title":"Transfer learning of optimal QAOA parameters in combinatorial optimization","author":"Montanez-Barrera","year":"2024","journal-title":"arXiv:2402.05549"},{"key":"ref23","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv:1701.07274"},{"key":"ref24","article-title":"Rethinking model-based, policy-based, and value-based reinforcement learning via the lens of representation complexity","author":"Feng","year":"2023","journal-title":"arXiv:2312.17248"},{"key":"ref25","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"30","author":"Nachum"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.10.032"},{"key":"ref27","article-title":"Deep reinforcement learning","author":"Li","year":"2018","journal-title":"arXiv:1810.06339"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3314732"},{"key":"ref29","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"arXiv:2307.15217"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.111651"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.09.029"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.012.2300052"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.073"},{"key":"ref34","article-title":"Transformers in reinforcement learning: A survey","author":"Agarwal","year":"2023","journal-title":"arXiv:2307.05979"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2024.107136"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3283523"},{"key":"ref37","article-title":"Reinforcement learning for combinatorial optimization: Leveraging uncertainty, structure and priors","author":"Grinsztajn","year":"2023"},{"key":"ref38","first-page":"1","article-title":"Learning combinatorial optimization algorithms over graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390240"},{"key":"ref40","article-title":"A contextual bandit bake-off","author":"Bietti","year":"2018","journal-title":"arXiv:1802.04064"},{"key":"ref41","first-page":"1","article-title":"Evolution-guided policy gradient in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khadka"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref43","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref44","first-page":"1","article-title":"Robust deep reinforcement learning through adversarial loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oikarinen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00494"},{"key":"ref48","first-page":"1","article-title":"Explicit inductive bias for transfer learning with convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1002\/nav.20261"},{"key":"ref51","article-title":"The transformer network for the traveling salesman problem","author":"Bresson","year":"2021","journal-title":"arXiv:2103.03012"},{"key":"ref52","article-title":"Efficient active search for combinatorial optimization problems","author":"Hottung","year":"2021","journal-title":"arXiv:2106.05126"},{"key":"ref53","article-title":"Approche poly\u00e8drale du probl\u00e8me de tourn\u00e9es de v\u00e9hicules","author":"Augerat","year":"1995"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1287\/opre.42.5.846"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2023.10.042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1050.0140"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2012.07.018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2016.01.059"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2018.8444393"},{"issue":"1","key":"ref60","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.cie.2011.08.018","article-title":"A genetic algorithm for the simultaneous delivery and pickup problems with time window","volume":"62","author":"Wang","year":"2012","journal-title":"Comput. Ind. Eng."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110203"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.05.010"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.orp.2016.09.002"},{"key":"ref64","article-title":"Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision","author":"Picard","year":"2021","journal-title":"arXiv:2109.08203"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2009.05.008"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-015-9281-6"},{"key":"ref67","article-title":"Un algorithme de g\u00e9n\u00e9ration de colonnes pour le probl\u00e8me de tourn\u00e9es de v\u00e9hicule avec demandes stochastiques","author":"Gauvin","year":"2012"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2011.09.023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11590-012-0555-8"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2010.05.048"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2014.07.001"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2021.102496"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.07.049"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.tre.2024.103677"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10766597.pdf?arnumber=10766597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T09:09:19Z","timestamp":1733908159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10766597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3505678","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}