{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T22:53:40Z","timestamp":1769813620184,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52472435"],"award-info":[{"award-number":["52472435"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22ZR1427700"],"award-info":[{"award-number":["22ZR1427700"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012472","name":"Education and Scientific Research Project of Shanghai","doi-asserted-by":"publisher","award":["B2023003"],"award-info":[{"award-number":["B2023003"]}],"id":[{"id":"10.13039\/501100012472","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s40747-025-02174-3","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T13:25:22Z","timestamp":1767014722000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A self-attention-based reinforcement learning approach for scheduling twin automated stacking cranes in container terminals"],"prefix":"10.1007","volume":"12","author":[{"given":"Liangcai","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8395-6813","authenticated-orcid":false,"given":"Yang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhennan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"key":"2174_CR1","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.cie.2015.04.026","volume":"89","author":"HJ Carlo","year":"2015","unstructured":"Carlo HJ, Mart\u00ednez-Acevedo FL (2015) Priority rules for twin automated stacking cranes that collaborate. Comput Ind Eng 89:23\u201333","journal-title":"Comput Ind Eng"},{"issue":"4","key":"2174_CR2","doi-asserted-by":"publisher","first-page":"760","DOI":"10.3390\/pr10040760","volume":"10","author":"J Chang","year":"2022","unstructured":"Chang J, Yu D, Hu Y et al (2022) Deep reinforcement learning for dynamic flexible job shop scheduling with random job arrival. Process 10(4):760","journal-title":"Process"},{"key":"2174_CR3","doi-asserted-by":"publisher","first-page":"102517","DOI":"10.1016\/j.rcim.2022.102517","volume":"81","author":"I Elguea-Aguinaco","year":"2023","unstructured":"Elguea-Aguinaco I, Serrano-Munoz A, Chrysostomou D et al (2023) A review on reinforcement learning for contact-rich robotic manipulation tasks. Robot Comput Integr Manuf 81:102517. https:\/\/doi.org\/10.1016\/j.rcim.2022.102517","journal-title":"Robot Comput Integr Manuf"},{"issue":"1","key":"2174_CR4","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.ejor.2017.01.037","volume":"261","author":"AH Gharehgozli","year":"2017","unstructured":"Gharehgozli AH, Vernooij FG, Zaerpour N (2017) A simulation study of the performance of twin automated stacking cranes at a seaport container terminal. Eur J Oper Res 261(1):108\u2013128. https:\/\/doi.org\/10.1016\/j.ejor.2017.01.037","journal-title":"Eur J Oper Res"},{"issue":"1","key":"2174_CR5","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.tre.2009.07.002","volume":"46","author":"J He","year":"2010","unstructured":"He J, Chang D, Mi W et al (2010) A hybrid parallel genetic algorithm for yard crane scheduling. Transp Res E Logist Transp Rev 46(1):136\u2013155. https:\/\/doi.org\/10.1016\/j.tre.2009.07.002","journal-title":"Transp Res E Logist Transp Rev"},{"issue":"1","key":"2174_CR6","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.aei.2014.09.003","volume":"29","author":"J He","year":"2015","unstructured":"He J, Huang Y, Yan W (2015) Yard crane scheduling in a container terminal for the trade-off between efficiency and energy consumption. Adv Eng Inform 29(1):59\u201375. https:\/\/doi.org\/10.1016\/j.aei.2014.09.003","journal-title":"Adv Eng Inform"},{"key":"2174_CR7","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.aei.2018.11.004","volume":"39","author":"J He","year":"2019","unstructured":"He J, Tan C, Zhang Y (2019) Yard crane scheduling problem in a container terminal considering risk caused by uncertainty. Adv Eng Inform 39:14\u201324. https:\/\/doi.org\/10.1016\/j.aei.2018.11.004","journal-title":"Adv Eng Inform"},{"key":"2174_CR8","doi-asserted-by":"publisher","first-page":"101292","DOI":"10.1016\/j.aei.2021.101292","volume":"48","author":"HP Hsu","year":"2021","unstructured":"Hsu HP, Tai HH, Wang CN et al (2021) Scheduling of collaborative operations of yard cranes and yard trucks for export containers using hybrid approaches. Adv Eng Inform 48:101292. https:\/\/doi.org\/10.1016\/j.aei.2021.101292","journal-title":"Adv Eng Inform"},{"issue":"6","key":"2174_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1080\/0951192X.2013.820347","volume":"27","author":"W Hu","year":"2014","unstructured":"Hu W, Min Z, Du B (2014) A novel algorithm based on the unified neutral theory of biodiversity and biogeography model for block allocation of outbound container. Int J Comput Integr Manuf 27(6):529\u2013546","journal-title":"Int J Comput Integr Manuf"},{"key":"2174_CR10","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.trc.2016.06.004","volume":"69","author":"ZH Hu","year":"2016","unstructured":"Hu ZH, Sheu JB, Luo JX (2016) Sequencing twin automated stacking cranes in a block at automated container terminal. Transp Res Part C Emerg Technol 69:208\u2013227. https:\/\/doi.org\/10.1016\/j.trc.2016.06.004","journal-title":"Transp Res Part C Emerg Technol"},{"key":"2174_CR11","unstructured":"Huang S, Onta\u00f1\u00f3n S (2020) A closer look at invalid action masking in policy gradient algorithms. arXiv preprint arXiv:2006.14171"},{"issue":"15","key":"2174_CR12","doi-asserted-by":"publisher","first-page":"3288","DOI":"10.3390\/electronics12153288","volume":"12","author":"X Jin","year":"2023","unstructured":"Jin X, Mi N, Song W et al (2023) Deep reinforcement learning for dynamic twin automated stacking cranes scheduling problem. Electron 12(15):3288. https:\/\/doi.org\/10.3390\/electronics12153288","journal-title":"Electron"},{"key":"2174_CR13","doi-asserted-by":"publisher","first-page":"110104","DOI":"10.1016\/j.cie.2024.110104","volume":"191","author":"X Jin","year":"2024","unstructured":"Jin X, Mi N, Song W et al (2024) Scheduling of twin automated stacking cranes based on deep reinforcement learning. Comput Ind Eng 191:110104. https:\/\/doi.org\/10.1016\/j.cie.2024.110104","journal-title":"Comput Ind Eng"},{"key":"2174_CR14","first-page":"21188","volume":"33","author":"YD Kwon","year":"2020","unstructured":"Kwon YD, Choo J, Kim B et al (2020) Pomo: Policy optimization with multiple optima for reinforcement learning. Adv Neural Inf Process Syst 33:21188\u201321198","journal-title":"Adv Neural Inf Process Syst"},{"issue":"5","key":"2174_CR15","doi-asserted-by":"publisher","first-page":"675","DOI":"10.3390\/jmse10050675","volume":"10","author":"J Li","year":"2022","unstructured":"Li J, Yang J, Xu B et al (2022) A flexible scheduling for twin yard cranes at container terminals considering dynamic cut-off time. J Mar Sci Eng 10(5):675","journal-title":"J Mar Sci Eng"},{"key":"2174_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107489","volume":"159","author":"S Luo","year":"2021","unstructured":"Luo S, Zhang L, Fan Y (2021) Dynamic multi-objective scheduling for flexible job shop by deep reinforcement learning. Comput Ind Eng 159:107489","journal-title":"Comput Ind Eng"},{"issue":"17","key":"2174_CR17","doi-asserted-by":"publisher","first-page":"2744","DOI":"10.3390\/math13172744","volume":"13","author":"Y Lv","year":"2025","unstructured":"Lv Y, Wang J, Liu Z et al (2025) From heuristics to multi-agent learning: A survey of intelligent scheduling methods in port seaside operations. Math 13(17):2744","journal-title":"Math"},{"key":"2174_CR18","doi-asserted-by":"publisher","first-page":"105400","DOI":"10.1016\/j.cor.2021.105400","volume":"134","author":"N Mazyavkina","year":"2021","unstructured":"Mazyavkina N, Sviridov S, Ivanov S et al (2021) Reinforcement learning for combinatorial optimization: A survey. Comput Oper Res 134:105400. https:\/\/doi.org\/10.1016\/j.cor.2021.105400","journal-title":"Comput Oper Res"},{"key":"2174_CR19","doi-asserted-by":"publisher","first-page":"102015","DOI":"10.1016\/j.aei.2023.102015","volume":"57","author":"AO Oladugba","year":"2023","unstructured":"Oladugba AO, Gheith M, Eltawil A (2023) A new solution approach for the twin yard crane scheduling problem in automated container terminals. Adv Eng Inform 57:102015. https:\/\/doi.org\/10.1016\/j.aei.2023.102015","journal-title":"Adv Eng Inform"},{"key":"2174_CR20","doi-asserted-by":"publisher","first-page":"106836","DOI":"10.1016\/j.knosys.2021.106836","volume":"217","author":"MI Radaideh","year":"2021","unstructured":"Radaideh MI, Shirvan K (2021) Rule-based reinforcement learning methodology to inform evolutionary algorithms for constrained optimization of engineering applications. Knowl-Based Syst 217:106836. https:\/\/doi.org\/10.1016\/j.knosys.2021.106836","journal-title":"Knowl-Based Syst"},{"issue":"1","key":"2174_CR21","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1080\/095372800232504","volume":"11","author":"V Subramaniam","year":"2000","unstructured":"Subramaniam V, Lee G, Hong G et al (2000) Dynamic selection of dispatching rules for job shop scheduling. Prod Plan Control 11(1):73\u201381. https:\/\/doi.org\/10.1080\/095372800232504","journal-title":"Prod Plan Control"},{"key":"2174_CR22","doi-asserted-by":"publisher","first-page":"110111","DOI":"10.1016\/j.cie.2024.110111","volume":"191","author":"Y Tang","year":"2024","unstructured":"Tang Y, Ye Z, Chen Y et al (2024) Regulating the imbalance for the container relocation problem: A deep reinforcement learning approach. Comput Ind Eng 191:110111. https:\/\/doi.org\/10.1016\/j.cie.2024.110111","journal-title":"Comput Ind Eng"},{"key":"2174_CR23","first-page":"1","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A (2017) Attention is all you need. Adv Neural Inf Process Syst 30:1","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"2174_CR24","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1108\/JMTM-06-2017-0112","volume":"30","author":"KT Vinod","year":"2019","unstructured":"Vinod KT, Prabagaran S, Joseph OA (2019) Dynamic due date assignment method a simulation study in a job shop with sequence-dependent setups. J Manuf Technol Manag 30(2):421\u2013437. https:\/\/doi.org\/10.1108\/JMTM-06-2017-0112","journal-title":"J Manuf Technol Manag"},{"key":"2174_CR25","doi-asserted-by":"publisher","first-page":"107969","DOI":"10.1016\/j.comnet.2021.107969","volume":"190","author":"L Wang","year":"2021","unstructured":"Wang L, Hu X, Wang Y et al (2021) Dynamic job-shop scheduling in smart manufacturing using deep reinforcement learning. Comput Netw 190:107969. https:\/\/doi.org\/10.1016\/j.comnet.2021.107969","journal-title":"Comput Netw"},{"key":"2174_CR26","doi-asserted-by":"publisher","first-page":"102657","DOI":"10.1016\/j.tre.2022.102657","volume":"160","author":"M Wang","year":"2022","unstructured":"Wang M, Zhou C, Wang A (2022) A cluster-based yard template design integrated with yard crane deployment using a placement heuristic. Transp Res E Logist Transp Rev 160:102657. https:\/\/doi.org\/10.1016\/j.tre.2022.102657","journal-title":"Transp Res E Logist Transp Rev"},{"key":"2174_CR27","doi-asserted-by":"publisher","unstructured":"Wang S, Li J, Jiao Q et al (2024) Design patterns of deep reinforcement learning models for job shop scheduling problems. J Intell Manuf. https:\/\/doi.org\/10.1007\/s10845-024-02454-8","DOI":"10.1007\/s10845-024-02454-8"},{"issue":"5","key":"2174_CR28","doi-asserted-by":"publisher","first-page":"892","DOI":"10.3390\/jmse11050892","volume":"11","author":"YZ Wang","year":"2023","unstructured":"Wang YZ, Hu ZH (2023) An iterative re-optimization framework for the dynamic scheduling of crossover yard cranes with uncertain delivery sequences. J Mar Sci Eng 11(5):892","journal-title":"J Mar Sci Eng"},{"key":"2174_CR29","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.cie.2018.12.039","volume":"128","author":"H XiaoLong","year":"2019","unstructured":"XiaoLong H, Qianqian W, Jiwei H (2019) Scheduling cooperative twin automated stacking cranes in automated container terminals. Comput Ind Eng 128:553\u2013558. https:\/\/doi.org\/10.1016\/j.cie.2018.12.039","journal-title":"Comput Ind Eng"},{"issue":"11","key":"2174_CR30","doi-asserted-by":"publisher","first-page":"5571","DOI":"10.1007\/s00170-022-10625-1","volume":"131","author":"W Yang","year":"2024","unstructured":"Yang W, Bao X, Zheng Y et al (2024) A digital twin framework for large comprehensive ports and a case study of qingdao port. Int J Adv Manuf Technol 131(11):5571\u20135588","journal-title":"Int J Adv Manuf Technol"},{"key":"2174_CR31","doi-asserted-by":"publisher","first-page":"123019","DOI":"10.1016\/j.eswa.2023.123019","volume":"245","author":"E Yuan","year":"2024","unstructured":"Yuan E, Wang L, Cheng S et al (2024) Solving flexible job shop scheduling problems via deep reinforcement learning. Expert Syst Appl 245:123019. https:\/\/doi.org\/10.1016\/j.eswa.2023.123019","journal-title":"Expert Syst Appl"},{"key":"2174_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123019","volume":"245","author":"E Yuan","year":"2024","unstructured":"Yuan E, Wang L, Cheng S et al (2024) Solving flexible job shop scheduling problems via deep reinforcement learning. Expert Syst Appl 245:123019","journal-title":"Expert Syst Appl"},{"key":"2174_CR33","doi-asserted-by":"publisher","unstructured":"Zhang C, Guan H, Yuan Y et al (2020) Machine learning-driven algorithms for the container relocation problem. Transp Res B Methodol 139:102\u2013131. https:\/\/doi.org\/10.1016\/j.trb.2020.05.017","DOI":"10.1016\/j.trb.2020.05.017"},{"key":"2174_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130184","volume":"638","author":"J Zhang","year":"2025","unstructured":"Zhang J, Jia Q, Zhang S et al (2025) Dynamic and prioritized task scheduling of heterogeneous multi-robot systems using deep reinforcement learning. Neurocomputing 638:130184","journal-title":"Neurocomputing"},{"key":"2174_CR35","doi-asserted-by":"publisher","unstructured":"Zhang Y, Bai R, Qu R et al (2022) A deep reinforcement learning based hyper-heuristic for combinatorial optimisation with uncertainties. Eur J Oper Res 300(2):418\u2013427. https:\/\/doi.org\/10.1016\/j.ejor.2021.10.032","DOI":"10.1016\/j.ejor.2021.10.032"},{"key":"2174_CR36","doi-asserted-by":"publisher","unstructured":"Zheng F, Man X, Chu F et al (2018) Two yard crane scheduling with dynamic processing time and interference. IEEE Trans Intell Transp Syst 19(12):3775\u20133784. https:\/\/doi.org\/10.1109\/TITS.2017.2780256","DOI":"10.1109\/TITS.2017.2780256"},{"issue":"13","key":"2174_CR37","doi-asserted-by":"publisher","first-page":"4132","DOI":"10.1080\/00207543.2018.1516903","volume":"57","author":"F Zheng","year":"2019","unstructured":"Zheng F, Man X, Chu F et al (2019) A two-stage stochastic programming for single yard crane scheduling with uncertain release times of retrieval tasks. Int J Prod Res 57(13):4132\u20134147. https:\/\/doi.org\/10.1080\/00207543.2018.1516903","journal-title":"Int J Prod Res"},{"key":"2174_CR38","doi-asserted-by":"publisher","first-page":"101966","DOI":"10.1016\/j.tre.2020.101966","volume":"138","author":"C Zhou","year":"2020","unstructured":"Zhou C, Lee BK, Li H (2020) Integrated optimization on yard crane scheduling and vehicle positioning at container yards. Transp Res E Logist Transp Rev 138:101966. https:\/\/doi.org\/10.1016\/j.tre.2020.101966","journal-title":"Transp Res E Logist Transp Rev"},{"key":"2174_CR39","doi-asserted-by":"publisher","first-page":"109258","DOI":"10.1016\/j.patcog.2022.109258","volume":"137","author":"W Zhu","year":"2023","unstructured":"Zhu W, Wang Z, Wang X et al (2023) A dual self-attention mechanism for vehicle re-identification. Pattern Recogn 137:109258. https:\/\/doi.org\/10.1016\/j.patcog.2022.109258","journal-title":"Pattern Recogn"},{"issue":"2","key":"2174_CR40","first-page":"1","volume":"15","author":"Z Zong","year":"2024","unstructured":"Zong Z, Tong X, Zheng M et al (2024) Reinforcement learning for solving multiple vehicle routing problem with time window. Transp Res E Logist Transp Rev 15(2):1\u201319","journal-title":"Transp Res E Logist Transp Rev"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02174-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-02174-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-02174-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T11:48:53Z","timestamp":1769773733000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-02174-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,29]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2174"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-02174-3","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,29]]},"assertion":[{"value":"22 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Material availability"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"44"}}