{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:33:28Z","timestamp":1785249208362,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"DGIST R&D Program of the Ministry of Science and ICT, South Korea","award":["23-DPIC-16"],"award-info":[{"award-number":["23-DPIC-16"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tii.2023.3292538","type":"journal-article","created":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T17:49:13Z","timestamp":1691516953000},"page":"2932-2943","source":"Crossref","is-referenced-by-count":17,"title":["Deep Reinforcement Learning-Driven Scheduling in Multijob Serial Lines: A Case Study in Automotive Parts Assembly"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8160-8952","authenticated-orcid":false,"given":"Sanghoon","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Electrical, Engineering, and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4627-3744","authenticated-orcid":false,"given":"Jinyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical, Engineering, and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0152-002X","authenticated-orcid":false,"given":"Gwangjin","family":"Wi","sequence":"additional","affiliation":[{"name":"Department of Electrical, Engineering, and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7115-9658","authenticated-orcid":false,"given":"Yuchang","family":"Won","sequence":"additional","affiliation":[{"name":"Department of Electrical, Engineering, and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2304-7106","authenticated-orcid":false,"given":"Yongsoon","family":"Eun","sequence":"additional","affiliation":[{"name":"Department of Electrical, Engineering, and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4807-6461","authenticated-orcid":false,"given":"Kyung-Joon","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Electrical, Engineering, and Computer Science, Daegu Gyeongbuk Institute of Science and Technology, Daegu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2843811"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2908210"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2017.1338779"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/4235.850651"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-005-0375-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2007.02.014"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2956762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1794075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WSC52266.2021.9715509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2017.8248100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2984739"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1717008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10696-020-09400-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfoodeng.2012.05.022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.11.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/0740817X.2012.721946"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2973432"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2022.3210259"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s21217366"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303831"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3163510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74958-5_41"},{"key":"ref26","first-page":"13544","article-title":"Rudder: Return decomposition for delayed rewards","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Arjona-Medina","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9056-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809799"},{"key":"ref29","article-title":"Acting in delayed environments with non-stationary Markov policies","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Derman","year":"2021"},{"key":"ref30","first-page":"8280","article-title":"Off-policy reinforcement learning with delayed rewards","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref32","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","volume":"500","author":"Kingma","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-75579-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2012.753166"},{"key":"ref37","article-title":"Toward implementation of production systems engineering (PSE) method for industry 4.0","author":"Won","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2014.948576"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2556078"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10440649\/10210628.pdf?arnumber=10210628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T01:53:35Z","timestamp":1709862815000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10210628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tii.2023.3292538","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}