{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T05:24:15Z","timestamp":1768541055818,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s10489-025-06880-w","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T01:10:14Z","timestamp":1760317814000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A multi-agent system for outbound container storage location assignment problem based on hierarchical reinforcement learning"],"prefix":"10.1007","volume":"55","author":[{"given":"Liangcai","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3169-9481","authenticated-orcid":false,"given":"Yuheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhennan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"6880_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/s00291-006-0059-y","author":"H-O G\u00fcnther","year":"2006","unstructured":"G\u00fcnther H-O, Kim K-H (2006) Container terminals and terminal operations. OR Spectr. https:\/\/doi.org\/10.1007\/s00291-006-0059-y","journal-title":"OR Spectr"},{"key":"6880_CR2","doi-asserted-by":"crossref","unstructured":"Wang S, Li J, Jiao Q, Ma F (2024) Design patterns of deep reinforcement learning models for job shop scheduling problems. J Intell Manuf, 1\u201319","DOI":"10.1007\/s10845-024-02454-8"},{"issue":"2","key":"6880_CR3","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","volume":"290","author":"Y Bengio","year":"2021","unstructured":"Bengio Y, Lodi A, Prouvost A (2021) Machine learning for combinatorial optimization: a methodological tour d\u2019horizon. Eur J Oper Res 290(2):405\u2013421","journal-title":"Eur J Oper Res"},{"key":"6880_CR4","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv:1707.06347"},{"key":"6880_CR5","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.jmsy.2015.02.010","volume":"36","author":"N Al-Dhaheri","year":"2015","unstructured":"Al-Dhaheri N, Diabat A (2015) The quay crane scheduling problem. J Manuf Syst 36:87\u201394","journal-title":"J Manuf Syst"},{"issue":"1","key":"6880_CR6","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1051\/ro\/2015048","volume":"51","author":"J Al-Hammadi","year":"2017","unstructured":"Al-Hammadi J, Diabat A (2017) An integrated berth allocation and yard assignment problem for bulk ports: formulation and case study. RAIRO-Oper Res 51(1):267\u2013284","journal-title":"RAIRO-Oper Res"},{"issue":"3","key":"6880_CR7","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1287\/trsc.2017.0736","volume":"52","author":"C Zhou","year":"2018","unstructured":"Zhou C, Chew EP, Lee LH (2018) Information-based allocation strategy for grid-based transshipment automated container terminal. Transp Sci 52(3):707\u2013721","journal-title":"Transp Sci"},{"key":"6880_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2020.101224","volume":"47","author":"X Hu","year":"2021","unstructured":"Hu X, Liang C, Chang D, Zhang Y (2021) Container storage space assignment problem in two terminals with the consideration of yard sharing. Adv Eng Inform 47:101224","journal-title":"Adv Eng Inform"},{"issue":"2","key":"6880_CR9","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1016\/j.ejor.2022.12.004","volume":"308","author":"C Zhang","year":"2023","unstructured":"Zhang C, Wang Q, Yuan G (2023) Novel models and algorithms for location assignment for outbound containers in container terminals. Eur J Oper Res 308(2):722\u2013737","journal-title":"Eur J Oper Res"},{"key":"6880_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocecoaman.2023.106915","volume":"247","author":"C Tan","year":"2024","unstructured":"Tan C, Qin T, He J, Wang Y, Yu H (2024) Yard space allocation of container port based on dual cycle strategy. Ocean Coastal Manage 247:106915","journal-title":"Ocean Coastal Manage"},{"key":"6880_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocecoaman.2024.107271","volume":"256","author":"Y Wang","year":"2024","unstructured":"Wang Y, Tan C, Wu H (2024) Slot assignment for outbound containers in storage space limited container terminal. Ocean Coast Manage 256:107271","journal-title":"Ocean Coast Manage"},{"issue":"1","key":"6880_CR12","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.ijpe.2010.09.019","volume":"135","author":"L Chen","year":"2012","unstructured":"Chen L, Lu Z (2012) The storage location assignment problem for outbound containers in a maritime terminal. Int J Prod Econ 135(1):73\u201380","journal-title":"Int J Prod Econ"},{"key":"6880_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.cor.2014.06.012","volume":"52","author":"C Zhang","year":"2014","unstructured":"Zhang C, Wu T, Zhong M, Zheng L, Miao L (2014) Location assignment for outbound containers with adjusted weight proportion. Comput Oper Res 52:84\u201393","journal-title":"Comput Oper Res"},{"issue":"7","key":"6880_CR14","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1080\/0740817X.2014.971201","volume":"47","author":"L Tang","year":"2015","unstructured":"Tang L, Jiang W, Liu J, Dong Y (2015) Research into container reshuffling and stacking problems in container terminal yards. IIE Trans 47(7):751\u2013766","journal-title":"IIE Trans"},{"key":"6880_CR15","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1007\/s13042-017-0676-6","volume":"9","author":"R Guerra-Olivares","year":"2018","unstructured":"Guerra-Olivares R, Smith NR, Gonz\u00e1lez-Ram\u00edrez RG, Garc\u00eda-Mendoza E, C\u00e1rdenas-Barr\u00f3n LE (2018) A heuristic procedure for the outbound container space assignment problem for small and midsize maritime terminals. Int J Mach Learn Cybern 9:1719\u20131732","journal-title":"Int J Mach Learn Cybern"},{"key":"6880_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2020.105142","volume":"127","author":"T Oelschl\u00e4gel","year":"2021","unstructured":"Oelschl\u00e4gel T, Knust S (2021) Solution approaches for storage loading problems with stacking constraints. Comput Oper Res 127:105142","journal-title":"Comput Oper Res"},{"issue":"9","key":"6880_CR17","doi-asserted-by":"publisher","first-page":"14336","DOI":"10.1109\/TITS.2021.3127552","volume":"23","author":"H Fan","year":"2021","unstructured":"Fan H, Peng W, Ma M, Yue L (2021) Storage space allocation and twin automated stacking cranes scheduling in automated container terminals. IEEE Trans Intell Transp Syst 23(9):14336\u201314348","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6880_CR18","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.trb.2022.02.012","volume":"158","author":"X Feng","year":"2022","unstructured":"Feng X, He Y, Kim K-H (2022) Space planning considering congestion in container terminal yards. Trans Res B: Methodological 158:52\u201377","journal-title":"Trans Res B: Methodological"},{"key":"6880_CR19","doi-asserted-by":"publisher","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. Knowledge-Based Systems 217:106836","journal-title":"Knowledge-Based Systems"},{"issue":"2","key":"6880_CR20","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.ejor.2021.10.032","volume":"300","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Bai R, Qu R, Tu C, Jin J (2022) A deep reinforcement learning based hyper-heuristic for combinatorial optimisation with uncertainties. Eur J Oper Res 300(2):418\u2013427","journal-title":"Eur J Oper Res"},{"key":"6880_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106508","volume":"123","author":"X Jin","year":"2023","unstructured":"Jin X, Duan Z, Song W, Li Q (2023) Container stacking optimization based on deep reinforcement learning. Eng Appl Artif Intell 123:106508","journal-title":"Eng Appl Artif Intell"},{"key":"6880_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110111","volume":"191","author":"Y Tang","year":"2024","unstructured":"Tang Y, Ye Z, Chen Y, Lu J, Huang S, Zhang J (2024) Regulating the imbalance for the container relocation problem: a deep reinforcement learning approach. Comput Ind Eng 191:110111","journal-title":"Comput Ind Eng"},{"issue":"2","key":"6880_CR23","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1007\/s10489-023-05013-5","volume":"54","author":"P Seurin","year":"2024","unstructured":"Seurin P, Shirvan K (2024) Assessment of reinforcement learning algorithms for nuclear power plant fuel optimization. Appl Intell 54(2):2100\u20132135","journal-title":"Appl Intell"},{"key":"6880_CR24","doi-asserted-by":"crossref","unstructured":"Seurin P, Shirvan K (2025) Surpassing legacy approaches to pwr core reload optimization with single-objective reinforcement learning. Nuclear Sci Eng, 1\u201332","DOI":"10.1080\/00295639.2025.2488702"},{"key":"6880_CR25","first-page":"331","volume":"2","author":"ML Puterman","year":"1990","unstructured":"Puterman ML (1990) Markov decision processes. Handb Oper Res Manage Sci 2:331\u2013434","journal-title":"Handb Oper Res Manage Sci"},{"key":"6880_CR26","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT press, Massachusetts"},{"key":"6880_CR27","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K et al (2017) Value-decomposition networks for cooperative multi-agent learning. arXiv:1706.05296"},{"issue":"5","key":"6880_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3453160","volume":"54","author":"S Pateria","year":"2021","unstructured":"Pateria S, Subagdja B, Tan A-h, Quek C (2021) Hierarchical reinforcement learning: a comprehensive survey. ACM Comput Surv 54(5):1\u201335","journal-title":"ACM Comput Surv"},{"key":"6880_CR29","unstructured":"Schulman J (2015) Trust region policy optimization. arXiv:1502.05477"},{"issue":"4","key":"6880_CR30","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1109\/TCCN.2019.2952909","volume":"5","author":"C Zhong","year":"2019","unstructured":"Zhong C, Lu Z, Gursoy MC, Velipasalar S (2019) A deep actor-critic reinforcement learning framework for dynamic multichannel access. IEEE Trans Cognit Commun Netw 5(4):1125\u20131139","journal-title":"IEEE Trans Cognit Commun Netw"},{"key":"6880_CR31","unstructured":"Vaswani A (2017) Attention is all you need. Adv Neural Inf Process Syst"},{"key":"6880_CR32","unstructured":"Huang S, Onta\u00f1\u00f3n S (2020) A closer look at invalid action masking in policy gradient algorithms. arXiv:2006.14171"},{"key":"6880_CR33","doi-asserted-by":"crossref","unstructured":"Gupta JK, Egorov M, Kochenderfer M (2017) Cooperative multi-agent control using deep reinforcement learning. In: Autonomous agents and multiagent systems: AAMAS 2017 Workshops, Best Papers, S\u00e3o Paulo, Brazil, May 8-12, 2017, Revised Selected Papers 16. Springer, pp 66\u201383","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"6880_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109650","volume":"185","author":"J-P Huang","year":"2023","unstructured":"Huang J-P, Gao L, Li X-Y, Zhang C-J (2023) A cooperative hierarchical deep reinforcement learning based multi-agent method for distributed job shop scheduling problem with random job arrivals. Comput Ind Eng 185:109650","journal-title":"Comput Ind Eng"},{"key":"6880_CR35","unstructured":"McCarthy J (1959) Programs with common sense. London"},{"issue":"4","key":"6880_CR36","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/PROC.1976.10159","volume":"64","author":"F Jelinek","year":"1976","unstructured":"Jelinek F (1976) Continuous speech recognition by statistical methods. Proc IEEE 64(4):532\u2013556","journal-title":"Proc IEEE"},{"key":"6880_CR37","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1023\/A:1015059928466","volume":"1","author":"H-G Beyer","year":"2002","unstructured":"Beyer H-G, Schwefel H-P (2002) Evolution strategies\u2013a comprehensive introduction. Nat Comput 1:3\u201352","journal-title":"Nat Comput"},{"issue":"1","key":"6880_CR38","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(1):281\u2013305","journal-title":"J Mach Learn Res"},{"key":"6880_CR39","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) Openai gym. arXiv:1606.01540"},{"issue":"268","key":"6880_CR40","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin A, Hill A, Gleave A, Kanervisto A, Ernestus M, Dormann N (2021) Stable-baselines3: reliable reinforcement learning implementations. J Mach Learn Res 22(268):1\u20138","journal-title":"J Mach Learn Res"},{"key":"6880_CR41","unstructured":"Radaideh MI, Du K, Seurin P, Seyler D, Gu X, Wang H, Shirvan K (2021) Neorl: neuroevolution optimization with reinforcement learning. arXiv:2112.07057"},{"key":"6880_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.anucene.2024.110582","volume":"205","author":"P Seurin","year":"2024","unstructured":"Seurin P, Shirvan K (2024) Multi-objective reinforcement learning-based approach for pressurized water reactor optimization. Ann Nucl Energy 205:110582","journal-title":"Ann Nucl Energy"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06880-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06880-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06880-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T15:42:13Z","timestamp":1762530133000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06880-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":42,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["6880"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06880-w","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"13 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 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 declare no conflicts of interest pertaining to the research, writing, and publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}],"article-number":"1016"}}