{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:42:01Z","timestamp":1770226921009,"version":"3.49.0"},"reference-count":36,"publisher":"Informa UK Limited","issue":"15","funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00337285"],"award-info":[{"award-number":["RS-2024-00337285"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2023-00218913"],"award-info":[{"award-number":["RS-2023-00218913"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1080\/00207543.2025.2461131","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T03:56:36Z","timestamp":1738814196000},"page":"5671-5691","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":4,"title":["Flexible material handling system for multi-load autonomous mobile robots in manufacturing environments: a hierarchical reinforcement learning approach"],"prefix":"10.1080","volume":"63","author":[{"given":"Keonwoo","family":"Park","sequence":"first","affiliation":[{"name":"Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seongbae","family":"Jo","sequence":"additional","affiliation":[{"name":"Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngchul","family":"Shin","sequence":"additional","affiliation":[{"name":"Ajou University","place":["Suwon-si, Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7072-1351","authenticated-orcid":false,"given":"Ilkyeong","family":"Moon","sequence":"additional","affiliation":[{"name":"Seoul National University","place":["Seoul, Republic of Korea"]},{"name":"Seoul National University","place":["Seoul, Republic of Korea"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,2,6]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2021.08.015"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2017.0803"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.06.005"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2022.1152"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2009.04.024"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/itor.2016.23.issue-3"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107782"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.9424"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1504\/EJIE.2020.112479"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2014.02.001"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.01.019"},{"key":"e_1_3_4_13_1","unstructured":"Han Beining Zhizhou Ren Zuofan Wu Yuan Zhou and Jian Peng. 2022. \u201cOff-Policy Reinforcement Learning with Delayed Rewards.\u201d In International Conference on Machine Learning 8280\u20138303. PMLR."},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.049"},{"key":"e_1_3_4_15_1","unstructured":"Kool Wouter Herke Van Hoof and Max Welling. 2018. \u201cAttention Learn to Solve Routing Problems!\u201d arXiv preprint arXiv:https:\/\/arxiv.org\/abs\/1803.08475."},{"key":"e_1_3_4_16_1","first-page":"3675","article-title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","volume":"29","author":"Kulkarni Tejas D.","year":"2016","unstructured":"Kulkarni, Tejas D., Karthik Narasimhan, Ardavan Saeedi, and Josh Tenenbaum. 2016. \u201cHierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation.\u201d Advances in Neural Information Processing Systems 29: 3675\u20133683.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3272661"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2021.102283"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2058432"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106208"},{"key":"e_1_3_4_21_1","first-page":"23609","article-title":"A Hierarchical Reinforcement Learning Based Optimization Framework for Large-Scale Dynamic Pickup and Delivery Problems","volume":"34","author":"Ma Yi","year":"2021","unstructured":"Ma, Yi, Xiaotian Hao, Jianye Hao, Jiawen Lu, Xing Liu, Tong Xialiang, Mingxuan Yuan, Zhigang Li, Jie Tang, and Zhaopeng Meng. 2021. \u201cA Hierarchical Reinforcement Learning Based Optimization Framework for Large-Scale Dynamic Pickup and Delivery Problems.\u201d Advances in Neural Information Processing Systems 34:23609\u201323620.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2015.10.017"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1968526"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2006.06.004"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.29.1.17"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2018.1524165"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3103416"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.11.036"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104055"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2023.109440"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1504\/EJIE.2015.067451"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2020.1000"},{"key":"e_1_3_4_34_1","unstructured":"Veli\u010dkovi\u0107 Petar Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2017. \u201cGraph Attention Networks.\u201d arXiv preprint arXiv:https:\/\/arxiv.org\/abs\/1710.10903."},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3031409"},{"key":"e_1_3_4_36_1","doi-asserted-by":"crossref","unstructured":"Zong Zefang Meng Zheng Yong Li and Depeng Jin. 2022. \u201cMapdp: Cooperative Multi-Agent Reinforcement Learning to Solve Pickup and Delivery Problems.\u201d In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 36 9980\u20139988.","DOI":"10.1609\/aaai.v36i9.21236"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106881"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2025.2461131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T07:49:42Z","timestamp":1753775382000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2025.2461131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,6]]},"references-count":36,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,8,3]]}},"alternative-id":["10.1080\/00207543.2025.2461131"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2025.2461131","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,6]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tprs20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=tprs20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2024-08-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}