{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:54:01Z","timestamp":1780674841506,"version":"3.54.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000015","name":"Advanced Research Projects Agency-Energy (ARPA-E), U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AR0001219"],"award-info":[{"award-number":["DE-AR0001219"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy, Lawrence Livermore National Laboratory","doi-asserted-by":"publisher","award":["DE-AC52-07NA27344"],"award-info":[{"award-number":["DE-AC52-07NA27344"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Lawrence Livermore National Security through LLC","award":["LLNL-JRNL_831362"],"award-info":[{"award-number":["LLNL-JRNL_831362"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3194267","type":"journal-article","created":{"date-parts":[[2022,7,27]],"date-time":"2022-07-27T19:24:38Z","timestamp":1658949878000},"page":"78702-78712","source":"Crossref","is-referenced-by-count":25,"title":["Deep Neural Network-Based Surrogate Model for Optimal Component Sizing of Power Converters Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"given":"Van-Hai","family":"Bui","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, College of Engineering and Computer Science, University of Michigan-Dearborn, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6439-7022","authenticated-orcid":false,"given":"Fangyuan","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, College of Engineering and Computer Science, University of Michigan-Dearborn, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1482-3078","authenticated-orcid":false,"given":"Wencong","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, College of Engineering and Computer Science, University of Michigan-Dearborn, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1979-2565","authenticated-orcid":false,"given":"Mengqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, College of Engineering and Computer Science, University of Michigan-Dearborn, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0501-8002","authenticated-orcid":false,"given":"Yi Lu","family":"Murphey","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, College of Engineering and Computer Science, University of Michigan-Dearborn, Dearborn, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe Leno","family":"Da Silva","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory (LLNL), Livermore, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Huang","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory (LLNL), Livermore, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9225-1584","authenticated-orcid":false,"given":"Lingxiao","family":"Xue","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruben","family":"Glatt","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory (LLNL), Livermore, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2015.07.194"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JESTPE.2017.2786588"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JESTPE.2021.3107500"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/en13030749"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2018.2872427"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034361"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2015.2397311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2008.2006026"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMAG.2018.2834488"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2012.2204711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2896235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2016.2574499"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643552"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GreenTech48523.2021.00024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3107535"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3007113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.2021.3126754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPEL.2020.2993635"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","volume-title":"Reinforcement Learning State-of-the Art","author":"Wiering","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref21","article-title":"Q-Prop: Sample-efficient policy gradient with an off-policy critic","volume-title":"arXiv:1611.02247","author":"Gu","year":"2016"},{"key":"ref22","article-title":"Soft actor-critic algorithms and applications","volume-title":"arXiv:1812.05905","author":"Haarnoja","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.seta.2021.101841"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2022.3168856"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2017.09.017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0731-1"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09841555.pdf?arnumber=9841555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T08:53:01Z","timestamp":1706777581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9841555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3194267","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}