{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T05:19:24Z","timestamp":1791868764626,"version":"4.3.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"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\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2021R1A4A2001824"],"award-info":[{"award-number":["2021R1A4A2001824"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Information and Communications Technology Planning and Evaluation"},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2020-0-00857"],"award-info":[{"award-number":["2020-0-00857"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2022-0-00124"],"award-info":[{"award-number":["2022-0-00124"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018058","name":"SK Hynix AICC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018058","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tase.2023.3308849","type":"journal-article","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:28:38Z","timestamp":1693852118000},"page":"5136-5148","source":"Crossref","is-referenced-by-count":5,"title":["Control of Fab Lifters via Deep Reinforcement Learning: A Semi-MDP Approach"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9472-467X","authenticated-orcid":false,"given":"Giho","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0131-5445","authenticated-orcid":false,"given":"Jaeuk","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0204-4213","authenticated-orcid":false,"given":"Gihun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5208-3854","authenticated-orcid":false,"given":"Joonrak","family":"Kim","sequence":"additional","affiliation":[{"name":"SK Hynix, Icheon, Gyeonggi-do, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-6169","authenticated-orcid":false,"given":"Insoon","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2013.6721742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/00207540801914934"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEEM.2011.6035471"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/09537280600900774"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2016.7822297"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2003.11.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2014.03.014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/asmc.2005.1438808"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2007.905991"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2006.03.034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2916622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2957184"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/23302674.2016.1244302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2012.2221087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2004.04.038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2004.04.039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2935469"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3149735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3039908"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2014.2306776"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2912018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2003.11.002"},{"key":"ref23","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0885-064X(89)90021-6"},{"key":"ref26","article-title":"Lower bound on the computational complexity of discounted Markov decision problems","author":"Chen","year":"2017","journal-title":"arXiv:1705.07312"},{"key":"ref27","first-page":"1017","article-title":"Improving elevator performance using reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"8","author":"Crites"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2015.7301554"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106749"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC52481.2021.9702196"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2002.1023172"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-015-8327-0"},{"issue":"4","key":"ref33","first-page":"167","article-title":"Optimization of lifter operations for inter-line transfers in semiconductor manufacturing facilities","volume":"8","author":"Lee","year":"2018","journal-title":"Int. J. Mech. Prod. Eng. Res. Develop."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1080\/00207548408942459"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref36","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref37","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","volume-title":"Proc. 2nd Conf. Learn. Dyn. Control","author":"Fan"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)58430-X"},{"key":"ref39","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Andrychowicz"},{"key":"ref40","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare"},{"key":"ref41","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Riedmiller"},{"key":"ref42","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref43","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref46","volume-title":"PyGame Learning Environment","author":"Tasfi","year":"2016"},{"key":"ref47","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref48","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref49","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref50","volume-title":"Gurobi Optimizer Reference Manual","year":"2023"},{"key":"ref51","first-page":"1","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kulkarni"},{"key":"ref52","first-page":"1","article-title":"Maximum entropy RL (provably) solves some robust RL problems","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Eysenbach"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref55","first-page":"1","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Clavera"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191234"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10718656\/10239211.pdf?arnumber=10239211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T17:27:32Z","timestamp":1729531652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10239211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":56,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tase.2023.3308849","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}