{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T06:11:40Z","timestamp":1781071900656,"version":"3.54.1"},"reference-count":61,"publisher":"Informa UK Limited","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72272027"],"award-info":[{"award-number":["72272027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72293563"],"award-info":[{"award-number":["72293563"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72322018"],"award-info":[{"award-number":["72322018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72071036"],"award-info":[{"award-number":["72071036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Dalian Scientific and Technological Talents Innovation Support Plan","award":["2022RG17"],"award-info":[{"award-number":["2022RG17"]}]},{"DOI":"10.13039\/501100011248","name":"State Key Laboratory of Synthetical Automation for Process Industries","doi-asserted-by":"publisher","award":["2022-KF-11-06"],"award-info":[{"award-number":["2022-KF-11-06"]}],"id":[{"id":"10.13039\/501100011248","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postgraduate Research Innovation"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2026,1,17]]},"DOI":"10.1080\/00207543.2024.2361449","type":"journal-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T08:26:12Z","timestamp":1718353572000},"page":"719-750","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":3,"title":["Large-scale dynamic surgical scheduling under uncertainty by hierarchical reinforcement learning"],"prefix":"10.1080","volume":"64","author":[{"given":"Lixiang","family":"Zhao","sequence":"first","affiliation":[{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]},{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5185-3324","authenticated-orcid":false,"given":"Han","family":"Zhu","sequence":"additional","affiliation":[{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]},{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]},{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafu","family":"Tang","sequence":"additional","affiliation":[{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]},{"name":"Dongbei University of Finance and Economics","place":["Dalian, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University","place":["Shenyang, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,6,14]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2011.02.025"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2850143"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2009.04.011"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.3182\/20050703-6-CZ-1902.01481"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10247-9"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2012.08.002"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-023-05168-x"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2022.103366"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.42.3.321"},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.12.006"},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2403"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2015.0658"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CASE48305.2020.9216743"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-015-0385-1"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/amp2.v4.4"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/poms.12993"},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106698"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01847-3"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2006.02.057"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0548(02)00105-3"},{"key":"e_1_3_4_25_1","unstructured":"Lillicrap Timothy P. Jonathan J. Hunt Alexander Pritzel Nicolas Heess Tom Erez Yuval Tassa David Silver and Daan Wierstra. 2015. \u201cContinuous Control with Deep Reinforcement Learning.\u201d arXiv preprint arXiv:1509.02971."},{"key":"e_1_3_4_26_1","first-page":"1","article-title":"Integrating Machine Learning and Mathematical Optimization for Job Shop Scheduling","volume":"1","author":"Liu Anbang","year":"2023","unstructured":"Liu, Anbang, Peter B. Luh, Kailai Sun, Mikhail A. Bragin, and Bing Yan. 2023. \u201cIntegrating Machine Learning and Mathematical Optimization for Job Shop Scheduling.\u201d IEEE Transactions on Automation Science and Engineering 1: 1\u201322.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2058432"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/poms.13012"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2012.01.013"},{"key":"e_1_3_4_30_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, et\u00a0al. 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_31_1","volume-title":"Cloud Computing: Theory and Practice","author":"Marinescu Dan C.","year":"2022","unstructured":"Marinescu, Dan C. 2022. Cloud Computing: Theory and Practice. Orlando, FL: Morgan Kaufmann."},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1060.0201"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107551"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_4_35_1","unstructured":"Ota Kei Tomoaki Oiki Devesh Jha Toshisada Mariyama and Daniel Nikovski. 2020. \u201cCan Increasing Input Dimensionality Improve Deep Reinforcement Learning?\u201d In International Conference on Machine Learning 7424\u20137433. PMLR."},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2006.03.059"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-2361-4"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3313998"},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.05.022"},{"key":"e_1_3_4_40_1","unstructured":"Schulman John Philipp Moritz Sergey Levine Michael Jordan and Pieter Abbeel. 2015. \u201cHigh-Dimensional Continuous Control Using Generalized Advantage Estimation.\u201d arXiv preprint arXiv:1506.02438."},{"key":"e_1_3_4_41_1","unstructured":"Schulman John Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. \u201cProximal Policy Optimization Algorithms.\u201d arXiv preprint arXiv:1707.06347."},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2019.05.002"},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10696-011-9111-6"},{"key":"e_1_3_4_44_1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Sutton, Richard S., and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. London: MIT Press."},{"key":"e_1_3_4_45_1","unstructured":"Valera H. H. Alvarez and M. Lu\u0161trek. 2022. \u201cA Multi-Agent RL Algorithm for Single-Day Operating Room Scheduling.\u201d In Workshops at 18th International Conference on Intelligent Environments (IE2022) Vol. 31 277. IOS Press."},{"key":"e_1_3_4_46_1","doi-asserted-by":"crossref","unstructured":"Van Hasselt Hado Arthur Guez and David Silver. 2016. \u201cDeep Reinforcement Learning with Double Q-Learning.\u201d In Proceedings of the AAAI Conference on Artificial Intelligence Vol.\u00a030.","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_4_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10878-015-9861-2"},{"key":"e_1_3_4_48_1","unstructured":"Wang Ziyu Tom Schaul Matteo Hessel Hado Hasselt Marc Lanctot and Nando Freitas. 2016. \u201cDueling Network Architectures for Deep Reinforcement Learning.\u201d In International Conference on Machine Learning 1995\u20132003. PMLR."},{"key":"e_1_3_4_49_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2050827"},{"key":"e_1_3_4_50_1","doi-asserted-by":"publisher","DOI":"10.1111\/poms.13949"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022672621406"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2023.3240106"},{"key":"e_1_3_4_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2015.1102356"},{"key":"e_1_3_4_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10729-023-09636-5"},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"e_1_3_4_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2011.07.019"},{"key":"e_1_3_4_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-006-0662-8"},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.1086\/716984"},{"key":"e_1_3_4_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2020.05.163"},{"key":"e_1_3_4_60_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2017.1355574"},{"key":"e_1_3_4_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10878-018-0322-6"},{"issue":"2","key":"e_1_3_4_62_1","first-page":"509","article-title":"Dynamic Pricing of Hotel Rooms Based on Reinforcement Learning with Unknown Demand Distribution","volume":"43","author":"Zhu Han","year":"2023","unstructured":"Zhu, Han, Min Zhang, and Jiafu Tang. 2023. \u201cDynamic Pricing of Hotel Rooms Based on Reinforcement Learning with Unknown Demand Distribution.\u201d Systems Engineering -- Theory & Practice 43 (2): 509\u2013523.","journal-title":"Systems Engineering -- Theory & Practice"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2024.2361449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:32:23Z","timestamp":1768296743000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2024.2361449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":61,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1,17]]}},"alternative-id":["10.1080\/00207543.2024.2361449"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2024.2361449","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,14]]},"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":"2023-12-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}