{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T23:44:05Z","timestamp":1782431045074,"version":"3.54.5"},"reference-count":53,"publisher":"Informa UK Limited","issue":"2","funder":[{"name":"BioFabUSA of Advanced Regenerative Manufacturing Institute","award":["T0171"],"award-info":[{"award-number":["T0171"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EEC-1648035"],"award-info":[{"award-number":["EEC-1648035"]}],"id":[{"id":"10.13039\/501100008982","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":[[2025,1,17]]},"DOI":"10.1080\/00207543.2023.2262043","type":"journal-article","created":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T06:58:17Z","timestamp":1695797897000},"page":"555-570","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":12,"title":["Deep reinforcement learning approach for dynamic capacity planning in decentralised regenerative medicine supply chains"],"prefix":"10.1080","volume":"63","author":[{"given":"Chin-Yuan","family":"Tseng","sequence":"first","affiliation":[{"name":"H. Milton Stewart School of Industrial & Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"},{"name":"Georgia Tech Manufacturing Institute, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Hsiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Georgia State University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kan","family":"Wang","sequence":"additional","affiliation":[{"name":"Georgia Tech Manufacturing Institute, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chelsea C.","family":"White III","sequence":"additional","affiliation":[{"name":"H. Milton Stewart School of Industrial & Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Wang","sequence":"additional","affiliation":[{"name":"H. Milton Stewart School of Industrial & Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2023,9,26]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-813314-9.00010-4"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1158\/2643-3230.BCD-21-0084"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1358"},{"issue":"6","key":"e_1_3_3_5_1","first-page":"3780","article-title":"Simulation-based Optimization of a Stochastic Supply Chain Considering Supplier Disruption: Agent-based Modeling and Reinforcement Learning","volume":"26","author":"Aghaie A.","year":"2019","unstructured":"Aghaie, A., and M. Hajian Heidary. 2019. \u201cSimulation-based Optimization of a Stochastic Supply Chain Considering Supplier Disruption: Agent-based Modeling and Reinforcement Learning.\u201d Scientia Iranica26 (6): 3780\u20133795.","journal-title":"Scientia Iranica"},{"key":"e_1_3_3_6_1","unstructured":"Alliance for Regenerative Medicine. 2021. \u201cRegenerative Medicine in 2021: A Year of Firsts & Records.\u201d https:\/\/alliancerm.org\/sector-report\/h1-2021-report\/."},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"e_1_3_3_8_1","unstructured":"Brockman Greg Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. \u201cOpenai gym.\u201d Preprint arXiv:1606.01540."},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2019.03.004"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2019.102112"},{"key":"e_1_3_3_11_1","first-page":"1587","volume-title":"International Conference on Machine Learning","author":"Fujimoto Scott","year":"2018","unstructured":"Fujimoto, Scott, Herke Hoof, and David Meger. 2018. \u201cAddressing Function Approximation Error in Actor-Critic Methods.\u201d In International Conference on Machine Learning, 1587\u20131596. Stockholmsm\u00e4ssan, Stockholm SWEDEN: Microtome Publishing."},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-5273(00)00156-0"},{"key":"e_1_3_3_13_1","unstructured":"Haarnoja Tuomas Aurick Zhou Pieter Abbeel and Sergey Levine. 2018. \u201cSoft Actor-Critic: Off-policy Maximum Entropy Deep Reinforcement Learning with A Stochastic Actor.\u201d In International Conference on Machine Learning 1861\u20131870.\u00a0Stockholmsm\u00e4ssan Stockholm SWEDEN: Microtome Publishing."},{"key":"e_1_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Hacha\u00efchi Yassine Yassine Chemingui and Mariem Affes. 2020. \u201cA Policy Gradient Based Reinforcement Learning Method for Supply Chain Management.\u201d In 2020 4th International Conference on Advanced Systems and Emergent Technologies (IC_ASET) 135\u2013140.\u00a0Hammamet Tunisia: IEEE.","DOI":"10.1109\/IC_ASET49463.2020.9318258"},{"key":"e_1_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Henderson Peter Riashat Islam Philip Bachman Joelle Pineau Doina Precup and David Meger. 2018. \u201cDeep Reinforcement Learning that Matters.\u201d In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 32.\u00a0New Orleans Louisiana: MIT Press.","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_3_16_1","unstructured":"Hill Ashley Antonin Raffin Maximilian Ernestus Adam Gleave Anssi Kanervisto Rene Traore and Prafulla Dhariwal et\u00a0al. 2018. \u201cStable Baselines.\u201d GitHub repository https:\/\/github.com\/hill-a\/stable-baselines."},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1756503"},{"key":"e_1_3_3_18_1","unstructured":"IMARC Group. 2021. \u201cRegenerative Medicine Market: Global Industry Trends Share Size Growth Opportunity and Forecast 2022\u20132027.\u201d https:\/\/www.imarcgroup.com\/regenerative-medicine-market."},{"issue":"37","key":"e_1_3_3_19_1","first-page":"34","article-title":"Hurricane Maria-lessons for the Drug Industry","volume":"96","author":"Jarvis Lisa M.","year":"2017","unstructured":"Jarvis, Lisa M. 2017. \u201cHurricane Maria-lessons for the Drug Industry.\u201d Chemical & Engineering News96 (37): 34\u201338.","journal-title":"Chemical & Engineering News"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2014.0575"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.08.046"},{"key":"e_1_3_3_22_1","unstructured":"Konda Vijay and John Dogan. Tsitsiklis. 1999. \u201cActor-critic Algorithms.\u201d In Advances in Neural Information Processing Systems Vol. 12.\u00a0Denver CO: MIT Press."},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Kosasih Edward Elson and Alexandra Brintrup. 2021. \u201cReinforcement Learning Provides a Flexible Approach for Realistic Supply Chain Safety Stock Optimisation.\u201d Preprint arXiv:2107.00913.","DOI":"10.1016\/j.ifacol.2022.09.609"},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcyt.2020.08.007"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10696-022-09475-6"},{"key":"e_1_3_3_26_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 Preprint arXiv:1509.02971."},{"key":"e_1_3_3_27_1","doi-asserted-by":"crossref","unstructured":"Littman Michael L. 1994. \u201cMarkov Games as A Framework for Multi-agent Reinforcement Learning.\u201d In Machine Learning Proceedings 1994 157\u2013163.\u00a0New Brunswick New Jersey: ELSEVIER.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"e_1_3_3_28_1","unstructured":"Lowe Ryan Yi Wu Aviv Tamar Jean Harb Pieter Abbeel and Igor Mordatch. 2017. \u201cMulti-agent Actor-critic for Mixed Cooperative-Competitive Environments.\u201d In Advances in Neural Information Processing Systems 30.\u00a0Long Beach CA: Curran Associates."},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2019.1693709"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1508520112"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.2217\/17460751.3.1.1"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1089\/gen.40.02.12"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2017.06.049"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1200\/OP.22.00315"},{"key":"e_1_3_3_35_1","unstructured":"Mnih Volodymyr Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. \u201cPlaying Atari with Deep Reinforcement Learning.\u201d Preprint arXiv:1312.5602."},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2014.10.015"},{"issue":"1","key":"e_1_3_3_38_1","first-page":"1","article-title":"A Deep Q-Network for the Beer Game: Deep Reinforcement Learning for Inventory Optimization","volume":"24","author":"Oroojlooyjadid Afshin","year":"2021","unstructured":"Oroojlooyjadid, Afshin, MohammadReza Nazari, Lawrence V. Snyder, and Martin Tak\u00e1\u010d. 2021. \u201cA Deep Q-Network for the Beer Game: Deep Reinforcement Learning for Inventory Optimization.\u201d Manufacturing & Service Operations Management 24 (1): 1\u2013689.","journal-title":"Manufacturing & Service Operations Management"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2020.573179"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41417-019-0157-z"},{"key":"e_1_3_3_41_1","unstructured":"Paszke Adam Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan and Trevor Killeen et al. 2019. \u201cPytorch: An Imperative Style High-Performance Deep Learning Library.\u201d In Advances in Neural Information Processing Systems 32.\u00a0Vancouver CANADA: Curran Associates."},{"key":"e_1_3_3_42_1","doi-asserted-by":"crossref","unstructured":"Peng Zedong Yi Zhang Yiping Feng Tuchao Zhang Zhengguang Wu and Hongye Su. 2019. \u201cDeep Reinforcement Learning Approach for Capacitated Supply Chain Optimization Under Demand Uncertainty.\u201d In 2019 Chinese Automation Congress (CAC) 3512\u20133517.\u00a0Hangzhou China: IEEE.","DOI":"10.1109\/CAC48633.2019.8997498"},{"key":"e_1_3_3_43_1","unstructured":"P\u00f6rtner Hans-Otto Debra C. Roberts H. Adams C. Adler P. Aldunce E. Ali and R. Ara Begum et al. 2022. \u201cClimate Change 2022: Impacts Adaptation and Vulnerability.\u201d In IPCC Sixth Assessment Report.\u00a0Geneva Switzerland."},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2140221"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJOPM-12-2021-0777"},{"key":"e_1_3_3_46_1","unstructured":"Schulman John Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. \u201cProximal Policy Optimization Algorithms.\u201d Preprint arXiv:1707.06347."},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107044"},{"key":"e_1_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_3_49_1","unstructured":"United States President and Council Of Economic Advisers. 2022. \u201cEconomic Report of the President 2022.\u201d"},{"key":"e_1_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.06.033"},{"key":"e_1_3_3_51_1","unstructured":"Vinyals Oriol Timo Ewalds Sergey Bartunov Petko Georgiev Alexander Sasha Vezhnevets Michelle Yeo and Alireza Makhzani et\u00a0al. 2017. \u201cStarcraft II: A New Challenge for Reinforcement Learning.\u201d Preprint arXiv:1708.04782."},{"key":"e_1_3_3_52_1","doi-asserted-by":"crossref","DOI":"10.1155\/2021\/6643131","article-title":"Solving a Joint Pricing and Inventory Control Problem for Perishables Via Deep Reinforcement Learning","volume":"2021","author":"Wang Rui","year":"2021","unstructured":"Wang, Rui, Xianghua Gan, Qing Li, and Xiao Yan. 2021. \u201cSolving a Joint Pricing and Inventory Control Problem for Perishables Via Deep Reinforcement Learning.\u201d Complexity 2021:6643131.","journal-title":"Complexity"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.2020927"},{"key":"e_1_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2010.05.005"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2023.2262043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T16:22:26Z","timestamp":1737390146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2023.2262043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,26]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1,17]]}},"alternative-id":["10.1080\/00207543.2023.2262043"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2023.2262043","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,26]]},"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":"2022-05-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}