{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:14:42Z","timestamp":1778148882925,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 107-2221-E-009-109-MY2"],"award-info":[{"award-number":["MOST 107-2221-E-009-109-MY2"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2987820","type":"journal-article","created":{"date-parts":[[2020,4,14]],"date-time":"2020-04-14T20:59:11Z","timestamp":1586897951000},"page":"71752-71762","source":"Crossref","is-referenced-by-count":251,"title":["Actor-Critic Deep Reinforcement Learning for Solving Job Shop Scheduling Problems"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2724-7199","authenticated-orcid":false,"given":"Chien-Liang","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5180-5181","authenticated-orcid":false,"given":"Chuan-Chin","family":"Chang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1611-4259","authenticated-orcid":false,"given":"Chun-Jan","family":"Tseng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2018.04.041"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref30","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASMC.2018.8373191"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2720178"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-14347-3_34"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2756594"},{"key":"ref11","first-page":"225","article-title":"Probabilistic learning combinations of local job-shop scheduling rules","author":"fisher","year":"1963","journal-title":"Industrial Scheduling"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2017.1355118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.12.009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1.2.117"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2006.07.003"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref18","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Resouce constrained project scheduling: An experimental investigation of heuristic scheduling techniques ()","author":"lawrence","year":"1984"},{"key":"ref28","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.6.2.154"},{"key":"ref27","first-page":"277","article-title":"The job shop scheduling problem: A concise survey and some recent developments","author":"pinson","year":"1995","journal-title":"Scheduling Theory and Its Applications"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(00)00087-7"},{"key":"ref6","first-page":"478","article-title":"Sequential optimality and coordination in multiagent systems","volume":"99","author":"boutilier","year":"1999","journal-title":"Proc IJCAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(98)00319-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/sj\/jors\/0411109"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2645699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/00207548908942666"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939827"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2016.1274680"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.3.2.149"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref22","first-page":"128","article-title":"A generic multi-agent reinforcement learning approach for scheduling problems","author":"jimenez","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.8.2.219"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.1995.479378"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940005"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2616347"},{"key":"ref26","author":"pinedo","year":"2016","journal-title":"Scheduling Theory Algorithms and Systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-017-1350-2"},{"key":"ref25","first-page":"9839","article-title":"Reinforcement learning for solving the vehicle routing problem","author":"nazari","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09066984.pdf?arnumber=9066984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:56:29Z","timestamp":1642002989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9066984\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2987820","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}