{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:52:05Z","timestamp":1783183925212,"version":"3.54.6"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T00:00:00Z","timestamp":1765238400000},"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":[[2025,12,9]]},"DOI":"10.1109\/cdc57313.2025.11312211","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"4714-4719","source":"Crossref","is-referenced-by-count":3,"title":["Discounted LQR: stabilizing (near-)optimal state-feedback laws"],"prefix":"10.1109","author":[{"given":"Jonathan","family":"de Brusse","sequence":"first","affiliation":[{"name":"Université de Lorraine,CNRS, CRAN,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jamal","family":"Daafouz","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, CRAN,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Granzotto","sequence":"additional","affiliation":[{"name":"University of Melbourne,Department of Electrical and Electronic Engineering,Parkville,VIC,Australia,3010"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Romain","family":"Postoyan","sequence":"additional","affiliation":[{"name":"Université de Lorraine,CNRS, CRAN,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dragan","family":"Ne\u0161i\u0107","sequence":"additional","affiliation":[{"name":"University of Melbourne,Department of Electrical and Electronic Engineering,Parkville,VIC,Australia,3010"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Optimal Control: Linear Quadratic Methods","author":"Anderson","year":"2007"},{"key":"ref2","article-title":"Dynamic Programming and Optimal Control","volume-title":"Athena Scientific","volume":"2","author":"Bertsekas","year":"2012"},{"issue":"5","key":"ref3","first-page":"430","article-title":"The discrete Riccati equation of optimal control","volume":"8","author":"Kucera","year":"1972","journal-title":"Kybernitika"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2616644"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.03.076"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2024.3490980"},{"key":"ref8","article-title":"Stabilizing dynamical systems via policy gradient methods","author":"Perdomo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Policy gradient convergence in discounted LQR","author":"Agazzi","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304202"},{"key":"ref11","article-title":"Learning stabilizing controllers of linear systems via discount policy gradient","author":"Zhao","year":"2021"},{"key":"ref12","article-title":"Lyapunov design for robust and efficient robotic reinforcement learning","volume-title":"Conference on Robot Learning","author":"Westenbroek"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.847055"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970777"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2470"},{"key":"ref17","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International Conference on Machine Learning","author":"Fazel"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/CDC57313.2025.11312211","article-title":"Discounted lqr: stabilizing (near-)optimal state-feedback laws","author":"de Brusse","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvc772kp"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3402941"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"}],"event":{"name":"2025 IEEE 64th Conference on Decision and Control (CDC)","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2025,12,9]]},"end":{"date-parts":[[2025,12,12]]}},"container-title":["2025 IEEE 64th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11311984\/11311968\/11312211.pdf?arnumber=11312211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:17:17Z","timestamp":1768292237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312211","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}