{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:54:19Z","timestamp":1767207259865,"version":"3.48.0"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3609488","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T17:31:22Z","timestamp":1757698282000},"page":"161355-161369","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning-Driven CMOS 8T-SRAM Design: Optimization With Tunable Trade-Offs in Power, Delay, and Area"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8794-8653","authenticated-orcid":false,"given":"Bisheng","family":"Zhu","sequence":"first","affiliation":[{"name":"School of CHIPS, Xi’an Jiaotong-Liverpool University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9827-2984","authenticated-orcid":false,"given":"Runhui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8366-2058","authenticated-orcid":false,"given":"Chonglin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Electronics, University of Liverpool, Liverpool, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen College of International Education, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zikai","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Physics and Optoelectronic Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2015.2474408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/isfee60884.2023.10637005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/itc-cscc55581.2022.9895022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/smacd61181.2024.10745428"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/meco58584.2023.10155066"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iseda62518.2024.10617712"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/date48585.2020.9116200"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/jssc.2007.917509"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/sym17040529"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/dac18074.2021.9586189"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icct52962.2021.9657899"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/apemc53576.2022.9888300"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iscas51556.2021.9401139"},{"key":"ref14","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"arXiv:1801.01290"},{"volume-title":"PyLTSpice","year":"2025","key":"ref15"},{"volume-title":"Digital Integrated Circuits","year":"1996","author":"Rabaey","key":"ref16"},{"key":"ref17","first-page":"417","article-title":"Off-policy temporal difference learning with function approximation","volume-title":"Proc. 18th Int. Conf. Mach. Learn. (ICML)","author":"Precup"},{"volume-title":"MOSFET Physics","year":"2025","key":"ref18"},{"issue":"1","key":"ref19","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of Pareto dominating policies","volume":"15","author":"Moffaert","year":"2014","journal-title":"J. Mach. Learn. Res."},{"volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","year":"2014","author":"Puterman","key":"ref20"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref21"},{"volume-title":"CMOS VLSI Design: A Circuits and Systems Perspective","year":"2015","author":"Weste","key":"ref22"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Mnih"},{"key":"ref24","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11162541.pdf?arnumber=11162541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:45:17Z","timestamp":1767206717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11162541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3609488","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}