{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T08:31:42Z","timestamp":1776241902309,"version":"3.50.1"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["20K14760"],"award-info":[{"award-number":["20K14760"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["23K03899"],"award-info":[{"award-number":["23K03899"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tac.2023.3264176","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T17:46:09Z","timestamp":1680543969000},"page":"363-370","source":"Crossref","is-referenced-by-count":8,"title":["Structured Output Feedback Control for Linear Quadratic Regulator Using Policy Gradient Method"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4672-9855","authenticated-orcid":false,"given":"Shokichi","family":"Takakura","sequence":"first","affiliation":[{"name":"Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1895-6548","authenticated-orcid":false,"given":"Kazuhiro","family":"Sato","sequence":"additional","affiliation":[{"name":"Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3087455"},{"key":"ref3","first-page":"7521","article-title":"Structured policy iteration for linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Park"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/20M1382386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147853"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992877"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104686"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/20M1329858"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2014.2322778"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-0348-0399-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2016.05.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/82592"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814952"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(01)00195-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2477810"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431290"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974997"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-014-0846-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref22","first-page":"1","article-title":"A natural policy gradient","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"14","author":"Kakade","year":"2001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9099-z"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10376321\/10091214.pdf?arnumber=10091214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T19:04:54Z","timestamp":1709147094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10091214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":23,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3264176","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}