{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:10:48Z","timestamp":1785420648141,"version":"3.56.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10384256","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"13-19","source":"Crossref","is-referenced-by-count":10,"title":["An Efficient Off-Policy Reinforcement Learning Algorithm for the Continuous-Time LQR Problem"],"prefix":"10.1109","author":[{"given":"Victor G.","family":"Lopez","sequence":"first","affiliation":[{"name":"Leibniz University Hannover, Institute of Automatic Control,Hannover,Germany,30167"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias A.","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Leibniz University Hannover, Institute of Automatic Control,Hannover,Germany,30167"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","volume-title":"Dynamic Programming and Optimal Control","volume":"I","author":"Bertsekas","year":"2005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2016.12.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147749"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3145693"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref10","first-page":"1","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Pro-ceedings of the 35th International Conference on Machine Learning","author":"Fazel","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2023.3235967"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837537"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3042876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.09.003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2021.09.005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2015.05.024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3934\/math.2022299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2011.03.038"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref23","volume-title":"Linear System Theory and Design","author":"Chen","year":"1999"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/s0024-3795(09)90001-5"},{"key":"ref25","volume-title":"Floating point operations in matrix-vector calculus","author":"Hunger","year":"2007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2959924"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2966717"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","location":"Singapore, Singapore","start":{"date-parts":[[2023,12,13]]},"end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10384256.pdf?arnumber=10384256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:30:49Z","timestamp":1737052249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10384256","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}