{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T08:58:48Z","timestamp":1781168328835,"version":"3.54.1"},"reference-count":52,"publisher":"Informa UK Limited","issue":"11","funder":[{"name":"Alibaba-NTU Global e-Sustainability CorpLab"}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Production Research"],"published-print":{"date-parts":[[2026,6,3]]},"DOI":"10.1080\/00207543.2025.2598025","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T19:48:54Z","timestamp":1764791334000},"page":"4217-4235","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":1,"title":["Information sharing and confidentiality: a federated multi-agent reinforcement learning approach for supply chain coordination"],"prefix":"10.1080","volume":"64","author":[{"given":"Bo","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computing and Data Science, NanyangTechnological University,\u00a0Singapore","place":["Republic of Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen Jun","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, NanyangTechnological University,\u00a0Singapore","place":["Republic of Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentong","family":"Cai","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, NanyangTechnological University,\u00a0Singapore","place":["Republic of Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allan N.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology and Research (A*STAR),\u00a0Singapore","place":["Republic of Singapore"]},{"name":"Nanyang Technological University","place":["Singapore, Republic of Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2098873"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2016.10.007"},{"key":"e_1_3_3_4_1","doi-asserted-by":"crossref","unstructured":"Barat S. H. Khadilkar H. Meisheri V. Kulkarni V. Baniwal P. Kumar and M. Gajrani. 2019. \u201cActor Based Simulation for Closed Loop Control of Supply Chain Using Reinforcement Learning.\u201d In\u00a0Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems Montreal QC Canada 1802\u20131804.","DOI":"10.65109\/RFYL9145"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1057\/jors.2010.188"},{"key":"e_1_3_3_6_1","unstructured":"Cai W. S. J. Turner and B. P. Gan. 2001. \u201cHierarchical Federations: An Architecture for Information Hiding.\u201d In Proceedings 15th Workshop on Parallel and Distributed Simulation Lake Arrowhead California USA 67\u201374."},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2104180"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/13675567.2020.1803246"},{"key":"e_1_3_3_9_1","doi-asserted-by":"crossref","unstructured":"Foerster J. G. Farquhar T. Afouras N. Nardelli and S. Whiteson. 2018. \u201cCounterfactual Multi-Agent Policy Gradients.\u201d In Proceedings of the AAAI Conference on Artificial Intelligence New Orleans Louisiana USA Vol. 32.","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2239393"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10207-024-00939-4"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/AUTOCOM64127.2025.10956464"},{"key":"e_1_3_3_13_1","unstructured":"Haarnoja T. A. Zhou P. Abbeel and S. Levine. 2018. \u201cSoft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.\u201d In International Conference on Machine Learning Stockholm Sweden 1861\u20131870."},{"key":"e_1_3_3_14_1","unstructured":"Hard A. K. Rao R. Mathews S. Ramaswamy F. Beaufays S. Augenstein H. Eichner C. Kiddon and D. Ramage.\u00a02018. \u201cFederated Learning for Mobile Keyboard Prediction.\u201d Accessed November 8 2018. https:\/\/arxiv.org\/abs\/1811.03604."},{"key":"e_1_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Hong Y. J. Vaidya N. Rizzo and Q. Liu. 2018. \u201cPrivacy-Preserving Linear Programming.\u201d In World Scientific Reference on Innovation: Volume 4: Innovation in Information Security Honolulu Hawaii 71\u201393.","DOI":"10.1142\/9789813149106_0004"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.2308\/isys-50692"},{"key":"e_1_3_3_17_1","unstructured":"Iqbal S. and F. Sha. 2019. \u201cActor-Attention-Critic for Multi-Agent Reinforcement Learning.\u201d In International Conference on Machine Learning Long Beach California USA 2961\u20132970."},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2309309"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-004-2069-8"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2023.109095"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106854"},{"key":"e_1_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352628"},{"key":"e_1_3_3_23_1","unstructured":"McMahan B. E. Moore D. Ramage S. Hampson and B. A. Y. Arcas. 2017. \u201cCommunication-Efficient Learning of Deep Networks from Decentralized Data.\u201d In Artificial Intelligence and Statistics Fort Lauderdale Florida USA 1273\u20131282."},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.09.004"},{"key":"e_1_3_3_25_1","unstructured":"Mouchet C. V. 2023. Multiparty Homomorphic Encryption: From Theory to Practice (Tech. Rep.). EPFL."},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1177\/0037549708100530"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.08.001"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.20473\/jisebi.7.2.138-148"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.1070.0219"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1108\/JEIM-08-2017-0114"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000430"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.10206"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/joom.v67.3"},{"key":"e_1_3_3_34_1","first-page":"1","article-title":"A Review on Reinforcement Learning Algorithms and Applications in Supply Chain Management","volume":"61","author":"Rolf B.","year":"2022","unstructured":"Rolf, B., I. Jackson, M. M\u00fcller, S. Lang, T. Reggelin, and D. Ivanov. 2022. \u201cA Review on Reinforcement Learning Algorithms and Applications in Supply Chain Management.\u201d International Journal of Production Research 61: 1\u201329.","journal-title":"International Journal of Production Research"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/poms.12717"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2019.106051"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.9734\/jerr\/2025\/v27i31439"},{"key":"e_1_3_3_38_1","unstructured":"Schulman J. F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. \u201cProximal Policy Optimization Algorithms.\u201d arXiv Preprint arXiv:1707.06347."},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.49.5.618.15147"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-69250-1"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJLM-06-2016-0150"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107312"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.2020927"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1287\/msom.1070.0176"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.2023833"},{"key":"e_1_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/info10080260"},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"e_1_3_3_48_1","doi-asserted-by":"crossref","unstructured":"Yang S. Y. Ogawa K. Ikeuchi Y. Akiyama and R. Shibasaki. 2019. \u201cFirm-Level Behavior Control after Large-Scale Urban Flooding Using Multi-Agent Deep Reinforcement Learning.\u201d In Proceedings of the 2nd ACM Sigspatial International Workshop on Geospatial Simulation Chicago Illinois 24\u201327.","DOI":"10.1145\/3356470.3365529"},{"key":"e_1_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3720539"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.3390\/su16229996"},{"issue":"6","key":"e_1_3_3_51_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3595185","article-title":"Trading off Privacy, Utility, and Efficiency in Federated Learning","volume":"14","author":"Zhang X.","year":"2023","unstructured":"Zhang, X., Y. Kang, K. Chen, L. Fan, and Q. Yang. 2023. \u201cTrading off Privacy, Utility, and Efficiency in Federated Learning.\u201d ACM Transactions on Intelligent Systems and Technology 14 (6): 1\u201332.","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2432469"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2164628"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2025.2598025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T08:12:22Z","timestamp":1781165542000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2025.2598025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":52,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2026,6,3]]}},"alternative-id":["10.1080\/00207543.2025.2598025"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2025.2598025","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"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":"2025-05-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}