{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:56:46Z","timestamp":1783090606825,"version":"3.54.6"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["NRF-2015R1D1A1A01057496"],"award-info":[{"award-number":["NRF-2015R1D1A1A01057496"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019211","name":"Institute of Engineering Research, Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019211","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3097254","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T22:28:11Z","timestamp":1627338491000},"page":"101390-101401","source":"Crossref","is-referenced-by-count":35,"title":["Deep Reinforcement Learning for Minimizing Tardiness in Parallel Machine Scheduling With Sequence Dependent Family Setups"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9414-4907","authenticated-orcid":false,"given":"Bohyung","family":"Paeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8890-7381","authenticated-orcid":false,"given":"In-Beom","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7505-110X","authenticated-orcid":false,"given":"Jonghun","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IEEM.2013.6962673"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2011.07.019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3012761"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/9.478328"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/jos.102"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0736-5845(02)00077-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-006-0662-8"},{"key":"ref36","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref35","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3011760"},{"key":"ref60","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.33.8.1035"},{"key":"ref61","first-page":"26","article-title":"Lecture 6.5-RMSPROP: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(99)00153-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-015-7215-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2004.07.006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3000781"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.04.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2956762"},{"key":"ref22","article-title":"RLScheduler: An automated HPC batch job scheduler using reinforcement learning","author":"zhang","year":"2019","journal-title":"arXiv 1910 08925"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106208"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2012.02.032"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-017-0549-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2019.06.007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2016.07.021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1717008"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref58","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.11.397"},{"key":"ref56","author":"harris","year":"2010","journal-title":"Digital Design and computer Architecture"},{"key":"ref55","article-title":"Manufacturing dispatching using reinforcement and transfer learning","author":"zheng","year":"2019","journal-title":"arXiv 1910 02035"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS.2018.8328189"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3029868"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2908210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-010-2824-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1504\/IJSOI.2016.080083"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3377929.3398150"},{"key":"ref12","first-page":"3279","article-title":"Unrelated parallel machine scheduling with sequence-and machine-dependent setup times and due date constraints","volume":"8","author":"ying","year":"2012","journal-title":"Int J Innov Comput Inf Control"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/07408179708966311"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2015.2511798"},{"key":"ref15","first-page":"1114","article-title":"A reinforcement learning approach to job-shop scheduling","volume":"95","author":"zhang","year":"1995","journal-title":"Proc IJCAI"},{"key":"ref16","first-page":"14","article-title":"Adaptive reactive job-shop scheduling with reinforcement learning agents","volume":"24","author":"gabel","year":"2008","journal-title":"Int J Info Technol Intell Comput"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASMC.2018.8373191"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2987820"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2601362"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1108\/AA-11-2018-0193"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-013-1339-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-4472-5_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/moor.15.3.483"},{"key":"ref49","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","volume":"70","author":"mirhoseini","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-016-8477-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-008-1917-3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940005"},{"key":"ref45","first-page":"9839","article-title":"Reinforcement learning for solving the vehicle routing problem","volume":"31","author":"nazari","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2017.05.026"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.03.039"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9148019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-018-1454-3"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09486959.pdf?arnumber=9486959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:03Z","timestamp":1639771023000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9486959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3097254","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}