{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T02:40:31Z","timestamp":1778121631509,"version":"3.51.4"},"reference-count":54,"publisher":"Informa UK Limited","issue":"9","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72471048"],"award-info":[{"award-number":["72471048"]}],"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":["71971044"],"award-info":[{"award-number":["71971044"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,5,3]]},"DOI":"10.1080\/00207543.2025.2597419","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:16:38Z","timestamp":1765152998000},"page":"3495-3517","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":2,"title":["An adaptive model-based deep reinforcement learning approach for matching-while-learning problem in shared manufacturing platforms"],"prefix":"10.1080","volume":"64","author":[{"given":"Liu","family":"Yang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China","place":["Chengdu, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Qu","sequence":"additional","affiliation":[{"name":"Department of Data and Systems Engineering, University of Hong Kong","place":["Hong Kong, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyu","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China","place":["Chengdu, People's Republic of China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengbin","family":"Chu","sequence":"additional","affiliation":[{"name":"Laboratoire GRETTIA-COSYS, Universit\u00e9 Gustave Eiffel, Noisy-le-Grand Cedex","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2025,12,7]]},"reference":[{"key":"e_1_3_5_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2024.02.027"},{"key":"e_1_3_5_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-54621-2_440-1"},{"key":"e_1_3_5_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2018.1535205"},{"key":"e_1_3_5_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.08.028"},{"key":"e_1_3_5_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126681"},{"key":"e_1_3_5_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2442549"},{"key":"e_1_3_5_8_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2398"},{"key":"e_1_3_5_9_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.45.1.24"},{"key":"e_1_3_5_10_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4134"},{"key":"e_1_3_5_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2025.111198"},{"key":"e_1_3_5_12_1","unstructured":"Hausknecht M. and P. Stone. 2015. \u201cDeep Recurrent Q-Learning for Partially Observable MDPs.\u201d In 2015 AAAI Fall Symposium Series 141. Washington DC: AAAI Press."},{"key":"e_1_3_5_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.09.045"},{"key":"e_1_3_5_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978520.28"},{"key":"e_1_3_5_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2230317"},{"key":"e_1_3_5_16_1","unstructured":"Jafferjee T. E. Imani E. Talvitie M. White and M. Bowling. 2020. \u201cHallucinating Value: A Pitfall of Dyna-Style Planning with Imperfect Environment Models.\u201d ArXiv preprint."},{"key":"e_1_3_5_17_1","unstructured":"Janner M. J. Fu M. Zhang and S. Levine. 2019. \u201cWhen to Trust Your Model: Model-Based Policy Optimization.\u201d In Advances in Neural Information Processing Systems 12498\u201312509. Vancouver: Curran Associates Inc.."},{"key":"e_1_3_5_18_1","unstructured":"Kaiser L. M. Babaeizadeh P. Milos B. Osinski R. H. Campbell K. Czechowski D. Erhan et al. 2020. \u201cModel-Based Reinforcement Learning for Atari.\u201d In Proceedings of the 8th International Conference on Learning Representations. Addis Ababa: ICLR."},{"key":"e_1_3_5_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2025.2539309"},{"key":"e_1_3_5_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-020-01552-7"},{"key":"e_1_3_5_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.6221021"},{"key":"e_1_3_5_22_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2431182"},{"key":"e_1_3_5_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2020.101991"},{"key":"e_1_3_5_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.9424"},{"key":"e_1_3_5_25_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2018.1449978"},{"key":"e_1_3_5_26_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.4034186"},{"key":"e_1_3_5_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2016.09.008"},{"key":"e_1_3_5_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_5_29_1","unstructured":"Nguyen N. M. A. Singh and K. Tran. 2018. \u201cImproving Model-Based RL with Adaptive Rollout Using Uncertainty Estimation.\u201d"},{"key":"e_1_3_5_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"e_1_3_5_31_1","first-page":"1","article-title":"Multi-agent Deep Reinforcement Learning for Integrated Production and Maintenance Optimisation in Shared Manufacturing","author":"Peng X.","year":"2025","unstructured":"Peng, X., S. Wang, and K. Wang. 2025. \u201cMulti-agent Deep Reinforcement Learning for Integrated Production and Maintenance Optimisation in Shared Manufacturing.\u201d International Journal of Production Research 1\u201320.","journal-title":"International Journal of Production Research"},{"key":"e_1_3_5_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110422"},{"key":"e_1_3_5_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2023.02.009"},{"key":"e_1_3_5_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2011.10.043"},{"key":"e_1_3_5_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/0951192X.2025.2504088"},{"key":"e_1_3_5_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1717008"},{"key":"e_1_3_5_37_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2024.05420"},{"key":"e_1_3_5_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1416"},{"key":"e_1_3_5_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110517"},{"key":"e_1_3_5_40_1","unstructured":"The Business Research Company. 2024. \u201cCloud Manufacturing Global Market Report 2024.\u201d https:\/\/www.thebusinessresearchcompany.com\/report\/cloud-manufacturing-global-market-report."},{"key":"e_1_3_5_41_1","unstructured":"Van Hasselt H. P. M. Hessel and J. Aslanides. 2019. \u201cWhen to Use Parametric Models in Reinforcement Learning?\u201d In Advances in Neural Information Processing Systems 14322\u201314333. Vancouver BC: Curran Associates Inc."},{"key":"e_1_3_5_42_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1774678"},{"key":"e_1_3_5_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2023.2197079"},{"key":"e_1_3_5_44_1","unstructured":"Wang T. X. Bao I. Clavera J. Hoang Y. Wen E. Langlois S. Zhang G. Zhang P. Abbeel and J. Ba. 2019. \u201cBenchmarking Model-Based Reinforcement Learning.\u201d ArXiv preprint."},{"key":"e_1_3_5_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36976-7"},{"key":"e_1_3_5_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117175"},{"key":"e_1_3_5_47_1","doi-asserted-by":"publisher","DOI":"10.1002\/nav.v67.8"},{"key":"e_1_3_5_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2021.09.013"},{"key":"e_1_3_5_49_1","doi-asserted-by":"publisher","DOI":"10.1080\/01605682.2024.2386364"},{"key":"e_1_3_5_50_1","doi-asserted-by":"publisher","DOI":"10.1002\/nav.70009"},{"key":"e_1_3_5_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106602"},{"key":"e_1_3_5_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2024.2309638"},{"key":"e_1_3_5_53_1","unstructured":"Zhang X. and W. C. Cheung. 2022. \u201cOnline Resource Allocation for Reusable Resources.\u201d ArXiv preprint."},{"key":"e_1_3_5_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3601"},{"key":"e_1_3_5_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2025.2597419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:27Z","timestamp":1777529607000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2025.2597419"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,7]]},"references-count":54,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,5,3]]}},"alternative-id":["10.1080\/00207543.2025.2597419"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2025.2597419","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,7]]},"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":"2025-07-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}