{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:01:26Z","timestamp":1780444886776,"version":"3.54.1"},"reference-count":93,"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-nc-nd\/4.0\/"}],"funder":[{"name":"General Scientific Research Fund of Zhejiang Provincial Education Department","award":["Y202351125"],"award-info":[{"award-number":["Y202351125"]}]},{"name":"Huzhou Natural Science Fund Project","award":["2023YZ35"],"award-info":[{"award-number":["2023YZ35"]}]},{"name":"Initial Scientific Research Fund of Talent Introduction in Huzhou College","award":["RK59004"],"award-info":[{"award-number":["RK59004"]}]},{"name":"Initial Scientific Research Fund of Talent Introduction in Huzhou College","award":["RK59006"],"award-info":[{"award-number":["RK59006"]}]},{"name":"Initial Scientific Research Fund of Talent Introduction in Huzhou College","award":["RK64001"],"award-info":[{"award-number":["RK64001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3412109","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:38:04Z","timestamp":1718131084000},"page":"85859-85879","source":"Crossref","is-referenced-by-count":10,"title":["A Mixed Generative Adversarial Imitation Learning Based Vehicle Path Planning Algorithm"],"prefix":"10.1109","volume":"12","author":[{"given":"Zan","family":"Yang","sequence":"first","affiliation":[{"name":"Public Teaching and Research Department, Huzhou College, Huzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4656-7040","authenticated-orcid":false,"given":"Wei","family":"Nai","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Huzhou College, Huzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5545-3574","authenticated-orcid":false,"given":"Dan","family":"Li","sequence":"additional","affiliation":[{"name":"Public Teaching and Research Department, Huzhou College, Huzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2210-5332","authenticated-orcid":false,"given":"Lu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Business, St. Bonaventure University, St. Bonaventure, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4277-1204","authenticated-orcid":false,"given":"Ziyu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Huzhou College, Huzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","volume-title":"Dynamic Programming and Optimal Control","author":"Bertsekas","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2020.08.017"},{"key":"ref3","first-page":"3293","article-title":"Learning to search in branch-and-bound algorithms","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"He"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/a11030031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2007.4425083"},{"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\/TVT.2016.2555853"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2765666"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963572"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3220842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2023.3239878"},{"key":"ref12","first-page":"2692","article-title":"Pointer networks","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Vinyals"},{"key":"ref13","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Sutskever"},{"key":"ref14","first-page":"1","article-title":"Reinforcement learning for solving the vehicle routing problem","volume-title":"Proc. 31th Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Nazari"},{"key":"ref15","first-page":"1","article-title":"Attention, learn to solve routing problems","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Kool"},{"key":"ref16","first-page":"1","article-title":"POMO: Policy optimization with multiple optima for reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Kwon"},{"key":"ref17","first-page":"6281","article-title":"Learning to perform local rewriting combinatorial optimization","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref18","first-page":"1","article-title":"A learning-based iterative method for solving vehicle routing problems","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Lu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3679145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593758"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71679-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X98001745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340639"},{"key":"ref26","article-title":"Learning by cheating","author":"Chen","year":"2019","journal-title":"arXiv:1912.12294"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911825"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3256704"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s20185034"},{"key":"ref31","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917713116"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2653850"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2017.2676018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"ref40","first-page":"2935","article-title":"Playing hard exploration games by watch YouTube","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref41","first-page":"1","article-title":"Imitating latent policies from observation","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Edward"},{"key":"ref42","article-title":"Deep Q-learning from demonstrations","author":"Hester","year":"2017","journal-title":"arXiv:1704.03732"},{"key":"ref43","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3241-z"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.12.005"},{"key":"ref46","first-page":"1","article-title":"Robust imitation of diverse behaviours","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref47","first-page":"1","article-title":"An imitation learning approach for cache replacement","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3191745"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3169207"},{"issue":"4","key":"ref50","first-page":"171","article-title":"Inverse reinforcement learning based optimal schedule generation approach for carrier aircraft on fight deck","volume":"35","author":"Li","year":"2013","journal-title":"J. Nat. Univ. Defense Technol."},{"issue":"3","key":"ref51","first-page":"208","article-title":"Survey of apprenticeship learning based on reward function learning","volume":"4","author":"Jin","year":"2009","journal-title":"CAAI Trans. Intell. Syst."},{"key":"ref52","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref53","first-page":"1","article-title":"Toward the fundamental limits of imitation learning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Rajaraman"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref55","first-page":"1449","article-title":"A game-theoretic approach to apprenticeship learning","volume-title":"Proc. 20th Int. Conf. Neural Inf. Process. Syst.","author":"Syed"},{"key":"ref56","article-title":"Learning human behaviors from motion capture by adversarial imitation","author":"Merel","year":"2017","journal-title":"arXiv:1707.02201"},{"key":"ref57","first-page":"321","volume-title":"Trends in Artificial Intelligence","author":"Geng","year":"2018"},{"key":"ref58","first-page":"3815","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref59","first-page":"1","article-title":"Third-person imitation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Stadie"},{"key":"ref60","article-title":"Generative adversarial imitation from observation","author":"Torabi","year":"2018","journal-title":"arXiv:1807.06158"},{"key":"ref61","first-page":"7472","article-title":"Multi-agent generative adversarial imitation learning","volume-title":"Proc. 31th Int. Conf. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref62","article-title":"Nearly minimax optimal adversarial imitation learning with known and unknown transitions","author":"Xu","year":"2021","journal-title":"arXiv:2106.10424"},{"key":"ref63","first-page":"64","article-title":"Optimality and approximation with policy gradient methods in Markov decision processes","volume-title":"Proc. 33rd Annu. Conf. Learn. Theory (COLT)","author":"Agarwal"},{"key":"ref64","first-page":"1","article-title":"Generative adversarial imitation learning","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref65","article-title":"Provably breaking the quadratic error compounding barrier in imitation learning, optimally","author":"Rajaraman","year":"2021","journal-title":"arXiv:2102.12948"},{"key":"ref66","article-title":"On generalization of adversarial imitation learning and beyond","author":"Xu","year":"2021","journal-title":"arXiv:2106.10424"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/978-3-030-30425-6","volume-title":"Advances in Neural Computation, Machine Learning, and Cognitive Research","author":"Kryzhanovsky","year":"2020"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1007\/978-3-030-65854-0","volume-title":"Software Quality: Future Perspectives on Software Engineering Quality","author":"Winkler","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.5220\/0010317710731081"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.110890"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1117\/12.2559453"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.11.005"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52152-3"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106844"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLIII-B2-2020-435-2020"},{"key":"ref76","article-title":"Optimization for deep learning: Theory and algorithms","author":"Sun","year":"2019","journal-title":"arXiv:1912.08957"},{"key":"ref77","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate O(1\/k2)","volume":"27","author":"Nesterov","year":"1983","journal-title":"Sov. Math. Doklady"},{"key":"ref78","first-page":"509","article-title":"On an approach to the construction of optimal methods of minimization of smooth convex functions","volume":"24","author":"Nesterov","year":"1988","journal-title":"Matematicheskie Metody Resheniya Ekonomicheskikh Zadach"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0552-5"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0629-5"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOS860"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1214\/11-AOS894"},{"key":"ref84","article-title":"Restricted strong convexity and weighted matrix completion: Optimal bounds with noise","author":"Negahban","year":"2010","journal-title":"arXiv:1009.2118"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488693"},{"key":"ref86","first-page":"638","article-title":"Fast matrix completion without the condition number","volume-title":"Proc. 27th Conf. Learn. Theory","author":"Hardt"},{"key":"ref87","first-page":"1","article-title":"A nonconvex optimization framework for low rank matrix estimation","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2598574"},{"key":"ref89","article-title":"Convergence analysis for rectangular matrix completion using Burer\u2013Monteiro factorization and gradient descent","author":"Zheng","year":"2016","journal-title":"arXiv:1605.07051"},{"key":"ref90","article-title":"Mixed policy gradient: Off-policy reinforcement learning driven jointly by data and model","author":"Guan","year":"2021","journal-title":"arXiv:2102.11513"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1017\/9781108348973"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/s101070100263"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-017-0357-2"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10552741.pdf?arnumber=10552741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:11:17Z","timestamp":1719349877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10552741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":93,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3412109","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}