{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:03:06Z","timestamp":1784736186468,"version":"3.55.0"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Basic Science Research Program through the National Research Foundation of Korea"},{"name":"Ministry of Education","award":["NRF-2019R1A6A1A03032119"],"award-info":[{"award-number":["NRF-2019R1A6A1A03032119"]}]},{"name":"Ministry of Education","award":["NRF-2021R1A6A1A03039981"],"award-info":[{"award-number":["NRF-2021R1A6A1A03039981"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3448535","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T17:33:40Z","timestamp":1724693620000},"page":"118442-118452","source":"Crossref","is-referenced-by-count":16,"title":["Reinforcement Learning-Based Control of DC-DC Buck Converter Considering Controller Time Delay"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0925-6358","authenticated-orcid":false,"given":"Donghun","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4658-7891","authenticated-orcid":false,"given":"Bongseok","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soonhyung","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9650-8479","authenticated-orcid":false,"given":"Ngoc-Duc","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0616-1449","authenticated-orcid":false,"given":"Min","family":"Kyu Sim","sequence":"additional","affiliation":[{"name":"Department of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3970-215X","authenticated-orcid":false,"given":"Young","family":"Il Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2022.2116362"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2017.2736023"},{"key":"ref3","volume-title":"Practical PID Control","author":"Visioli","year":"2006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/OJIA.2020.3020184"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2937878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-022-07913-6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref8","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3107535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PEDG51384.2021.9494214"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA51954.2021.9516099"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3005071"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3192676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3170608"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2023.105499"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2020.106657"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.076"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3325590"},{"key":"ref19","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref21","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref23","first-page":"1","article-title":"Real-time reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ramstedt"},{"key":"ref24","article-title":"Efficiency of synchronous versus nonsynchronous buck converters","author":"Nowakowski","year":"2009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Sutton"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00079"},{"key":"ref29","article-title":"Equivalence between policy gradients and soft Q-learning","author":"Schulman","year":"2017","journal-title":"arXiv:1704.06440"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2013.0115"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10646892.pdf?arnumber=10646892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:21:21Z","timestamp":1725693681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10646892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3448535","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}