{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:22:43Z","timestamp":1777306963607,"version":"3.51.4"},"reference-count":41,"publisher":"Informa UK Limited","issue":"11","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173017"],"award-info":[{"award-number":["62173017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002358","name":"Beihang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002358","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":[[2024,6,2]]},"DOI":"10.1080\/00207543.2023.2253326","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T12:21:04Z","timestamp":1694089264000},"page":"4014-4030","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":23,"title":["An improved deep reinforcement learning-based scheduling approach for dynamic task scheduling in cloud manufacturing"],"prefix":"10.1080","volume":"62","author":[{"given":"Xiaohan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, People's Republic of China"},{"name":"State Key Laboratory of Intelligent Manufacturing System Technology, Beijing, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2165-775X","authenticated-orcid":false,"given":"Yongkui","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechano-Electronic Engineering, Xidian University, Xi'an, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanjun","family":"Laili","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, People's Republic of China"},{"name":"Zhongguancun Laboratory, Beijing, People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2023,9,7]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2148767"},{"key":"e_1_3_4_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.2013566"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011253011638"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.v32.11"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02884-1"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3208942"},{"key":"e_1_3_4_8_1","unstructured":"Gal Yarin and Zoubin Ghahramani. 2016. \u201cDropout as A Bayesian Approximation: Representing Model Uncertainty in Deep Learning.\u201d In International Conference on Machine Learning New York USA 1050\u20131059. PMLR."},{"key":"e_1_3_4_9_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 Vienna Austria 1861\u20131870. PMLR."},{"key":"e_1_3_4_10_1","doi-asserted-by":"crossref","unstructured":"Halty Agust\u00edn Rodrigo S\u00e1nchez Valent\u00edn V\u00e1zquez V\u00edctor Viana Pedro Pi\u00f1eyro and Daniel Alejandro Rossit. 2020. \u201cScheduling in Cloud Manufacturing Systems: Recent Systematic Literature Review.\u201d","DOI":"10.3934\/mbe.2020377"},{"key":"e_1_3_4_11_1","doi-asserted-by":"crossref","unstructured":"Hoel Carl-Johan Krister Wolff and Leo Laine. 2020. \u201cTactical Decision-Making in Autonomous Driving by Reinforcement Learning with Uncertainty Estimation.\u201d In 2020 IEEE Intelligent Vehicles Symposium (IV) Las Vegas USA 1563\u20131569. IEEE.","DOI":"10.1109\/IV47402.2020.9304614"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.1142\/S1793962323410283"},{"key":"e_1_3_4_13_1","unstructured":"Huang Shengyi and Santiago Onta\u00f1\u00f3n. 2020. \u201cA Closer Look at Invalid Action Masking in Policy Gradient Algorithms.\u201d Preprint http:\/\/arXiv:2006.14171."},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.v31.20"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.2507\/IJSIMM"},{"key":"e_1_3_4_16_1","unstructured":"Levine Sergey Aviral Kumar George Tucker and Justin Fu. 2020. \u201cOffline Reinforcement Learning: Tutorial Review and Perspectives on Open Problems.\u201d Preprint arXiv:2005.01643."},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2018.2842085"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2018.09.002"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.6221021"},{"issue":"1","key":"e_1_3_4_20_1","first-page":"1","article-title":"Cloud Manufacturing: a New Service-oriented Networked Manufacturing Model","volume":"16","author":"Li Bohu","year":"2010","unstructured":"Li, Bohu, Lin Zhang, Shilong Wang, Fei Tao, Jw Cao, Xd Jiang, Xiao Song, and Xudong Chai. 2010. \u201cCloud Manufacturing: a New Service-oriented Networked Manufacturing Model.\u201d Computer Integrated Manufacturing Systems 16 (1): 1\u20137.","journal-title":"Computer Integrated Manufacturing Systems"},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2020.101991"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102323"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102454"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2018.1449978"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2016.09.008"},{"key":"e_1_3_4_26_1","doi-asserted-by":"crossref","unstructured":"Mashhadi Farshad and Sergio A. Salinas Monroy. 2020. \u201cDeep Learning for Optimal Resource Allocation in IoT-Enabled Additive Manufacturing.\u201d In 2020 IEEE 6th World Forum on Internet of Things (WF-IoT) New Orleans USA 1\u20136. IEEE.","DOI":"10.1109\/WF-IoT48130.2020.9221038"},{"key":"e_1_3_4_27_1","unstructured":"Nair Ashvin Abhishek Gupta Murtaza Dalal and Sergey Levine. 2020. \u201cAwac: Accelerating Online Reinforcement Learning with Offline Datasets.\u201d Preprint arXiv:2006.09359."},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1973138"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1870013"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2023.02.009"},{"key":"e_1_3_4_31_1","doi-asserted-by":"crossref","unstructured":"Qin Ruochen and Chen Lu. 2019. \u201cResearch on Measurement Methods of Transferability between Different Domains in Transfer Learning.\u201d In 2019 CAA Symposium on Fault Detection Supervision and Safety for Technical Processes (SAFEPROCESS) Xiamen China 926\u2013931. IEEE.","DOI":"10.1109\/SAFEPROCESS45799.2019.9213266"},{"key":"e_1_3_4_32_1","unstructured":"Schulman John Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. \u201cProximal Policy Optimization Algorithms.\u201d Preprint http:\/\/arXiv:1707.06347."},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2022.2025554"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2021.107969"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1774678"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.08.004"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.08.013"},{"key":"e_1_3_4_38_1","unstructured":"Wu Yue Shuangfei Zhai Nitish Srivastava Joshua Susskind Jian Zhang Ruslan Salakhutdinov and Hanlin Goh. 2021. \u201cUncertainty Weighted Actor-Critic for Offline Reinforcement Learning.\u201d Preprint arXiv:2105.08140."},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1943037"},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3178410"},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.9424"},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/Access.6287639"}],"container-title":["International Journal of Production Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/00207543.2023.2253326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T14:20:09Z","timestamp":1713882009000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/00207543.2023.2253326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,7]]},"references-count":41,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,6,2]]}},"alternative-id":["10.1080\/00207543.2023.2253326"],"URL":"https:\/\/doi.org\/10.1080\/00207543.2023.2253326","relation":{},"ISSN":["0020-7543","1366-588X"],"issn-type":[{"value":"0020-7543","type":"print"},{"value":"1366-588X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,7]]},"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":"2023-04-26","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}