{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T19:16:23Z","timestamp":1784142983424,"version":"3.55.0"},"reference-count":51,"publisher":"Informa UK Limited","issue":"10","funder":[{"name":"Research Grants Council of the Hong Kong SAR of China"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003803","name":"The University of Hong Kong","doi-asserted-by":"publisher","award":["RGC Project No. 15219422 & G-HKU502\/22, NSFC Project No. 72201228, HKU Project No. 2201100548 & 109000053"],"award-info":[{"award-number":["RGC Project No. 15219422 & G-HKU502\/22, NSFC Project No. 72201228, HKU Project No. 2201100548 & 109000053"]}],"id":[{"id":"10.13039\/501100003803","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong-Hong Kong Technology Cooperation Funding Schem","award":["GHP\/321\/22SZ"],"award-info":[{"award-number":["GHP\/321\/22SZ"]}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1080\/00207543.2024.2430457","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T15:59:36Z","timestamp":1733327976000},"page":"3760-3797","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":3,"title":["A joint work package sizing and scheduling problem considering resource constraints with a look-ahead heterogeneous reinforcement learning method"],"prefix":"10.1080","volume":"63","author":[{"given":"Nianmin","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Hong Kong","place":["Hong Kong, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Hong Kong","place":["Hong Kong, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Gao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology","place":["Hefei, People's Republic of China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2005.04.030"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2023.102628"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2294109"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.1164"},{"key":"e_1_3_4_6_1","volume-title":"Project Scheduling: A Research Handbook","author":"Demeulemeester Erik Leuven","year":"2006","unstructured":"Demeulemeester, Erik Leuven, and Willy S. Herroelen. 2006. Project Scheduling: A Research Handbook. Vol. 49. New York: Springer Science & Business Media."},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022283403119"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.104958"},{"key":"e_1_3_4_9_1","unstructured":"Grudzien Jakub Christian A. Schroeder De Witt and Jakob Foerster. 2022. \u201cMirror Learning: A Unifying Framework of Policy Optimisation.\u201d In International Conference on Machine Learning 7825\u20137844. PMLR."},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2020.1714455"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2020.3033072"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.05.004"},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.3934\/jimo.2020077"},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-014-1395-5"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.5267\/j.jpm.2019.11.001"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.05.070"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-022-02037-5"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01847-3"},{"key":"e_1_3_4_19_1","unstructured":"Kuba Jakub Grudzien Ruiqing Chen Muning Wen Ying Wen Fanglei Sun Jun Wang and Yaodong Yang. 2021. \u201cTrust Region Policy Optimisation in Multi-Agent Reinforcement Learning.\u201d preprint arXiv:2109.11251."},{"key":"e_1_3_4_20_1","unstructured":"Kuba Jakub Grudzien Xidong Feng Shiyao Ding Hao Dong Jun Wang and Yaodong Yang. 2022. \u201cHeterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative Marl.\u201d preprint arXiv:2208.01682."},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-007-0021-0"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103738"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1767"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.104083"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110115"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106961"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2018.02.308"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12891"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1788737"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2023.105003"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.05.014"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-08-096704-2.50001-6"},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1870013"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.01.063"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470172339"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2022.09.033"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2023.10.046"},{"key":"e_1_3_4_38_1","unstructured":"Schulman John Sergey Levine Pieter Abbeel Michael Jordan and Philipp Moritz. 2015. \u201cTrust Region Policy Optimization.\u201d In International Conference on Machine Learning 1889\u20131897. PMLR."},{"key":"e_1_3_4_39_1","unstructured":"Schulman John Philipp Moritz Sergey Levine Michael Jordan and Pieter Abbeel. 2015. \u201cHigh-Dimensional Continuous Control Using Generalized Advantage Estimation.\u201d preprint arXiv:1506.02438."},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1924411"},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/15623599.2021.1907525"},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2019.05.004"},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2007.03.032"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110018"},{"key":"e_1_3_4_45_1","unstructured":"Wang Xihuai Zheng Tian Ziyu Wan Ying Wen Jun Wang and Weinan Zhang. 2023. \u201cOrder Matters: Agent-By-Agent Policy Optimization.\u201d preprint arXiv:2302.06205."},{"key":"e_1_3_4_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102324"},{"key":"e_1_3_4_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2253326"},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.08.004"},{"key":"e_1_3_4_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110083"},{"key":"e_1_3_4_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122092"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120571"},{"issue":"150","key":"e_1_3_4_52_1","first-page":"1","article-title":"Malib: A Parallel Framework for Population-Based Multi-Agent Reinforcement Learning","volume":"24","author":"Zhou Ming","year":"2023","unstructured":"Zhou, Ming, Ziyu Wan, Hanjing Wang, Muning Wen, Runzhe Wu, Ying Wen, Yaodong Yang, Yong Yu, Jun Wang, and Weinan Zhang. 2023. \u201cMalib: A Parallel Framework for Population-Based Multi-Agent Reinforcement Learning.\u201d Journal of Machine Learning Research 24 (150): 1\u201312. http:\/\/jmlr.org\/papers\/v24\/22-0169.html","journal-title":"Journal of Machine Learning Research"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2024.2430457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:07:31Z","timestamp":1748390851000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2024.2430457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,5,19]]}},"alternative-id":["10.1080\/00207543.2024.2430457"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2024.2430457","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"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":"2024-04-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}