{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:48:14Z","timestamp":1776358094829,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T00:00:00Z","timestamp":1665273600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,9]]},"DOI":"10.1109\/smc53654.2022.9945585","type":"proceedings-article","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T20:49:04Z","timestamp":1668804544000},"page":"3222-3227","source":"Crossref","is-referenced-by-count":5,"title":["Learning to Schedule Job-Shop Problems via Hierarchical Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zijun","family":"Liao","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Qiwen","family":"Li","sequence":"additional","affiliation":[{"name":"Brown University,Department of Computer Science,Providence,RI,USA"}]},{"given":"Yuanzhi","family":"Dai","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Software Engineering,Zhuhai,China"}]},{"given":"Zizhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref39","author":"sutton","year":"1984","journal-title":"Temporal credit assignment in reinforcement learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref33","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"In International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref30","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"In International Conference on Machine Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.03.039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.12785\/ijcds\/040207"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASMC.2018.8373191"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1057\/jors.1990.166","article-title":"OR-Library: distributing test problems by electronic mail","volume":"41","author":"beasley","year":"1990","journal-title":"Journal of the Operational Research Society"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2018.2862380"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2019.02.101"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-020-01612-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5220\/0009095207660772"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378191"},{"key":"ref16","article-title":"Reinforcement learning on job shop scheduling problems using graph networks","author":"hameed","year":"2020","journal-title":"arXiv preprint arXiv 2009 02026"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.02.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1870013"},{"key":"ref19","first-page":"1621","article-title":"Learning to dispatch for job shop scheduling via deep reinforcement learning","volume":"33","author":"zhang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Multi-level discovery of deep options","author":"fox","year":"2017","journal-title":"arXiv preprint arXiv 1703 08294"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.8.2.219"},{"key":"ref27","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"arXiv preprint arXiv 1704 03012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-004-2296-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1.2.117"},{"key":"ref29","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"gupta","year":"2019","journal-title":"arXiv preprint arXiv 1910 10817"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1965.7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-0303-9_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF01721162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.106982"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2020.1794075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00052"},{"key":"ref22","first-page":"29","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"5","article-title":"Feudal reinforcement learning","author":"dayan","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Learning multi-level hierarchies with hindsight","author":"levy","year":"2017","journal-title":"arXiv preprint arXiv 1712 00948"},{"key":"ref23","first-page":"31","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"}],"event":{"name":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Prague, Czech Republic","start":{"date-parts":[[2022,10,9]]},"end":{"date-parts":[[2022,10,12]]}},"container-title":["2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9945068\/9945069\/09945585.pdf?arnumber=9945585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:55:24Z","timestamp":1670874924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9945585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,9]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/smc53654.2022.9945585","relation":{},"subject":[],"published":{"date-parts":[[2022,10,9]]}}}