{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:28:21Z","timestamp":1768314501734,"version":"3.49.0"},"reference-count":30,"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\/cdc57313.2025.11312822","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"3761-3768","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Continuous-time LQR and Reinforcement Learning via Gradient Flow of the Bellman Error"],"prefix":"10.1109","author":[{"given":"Armin","family":"Gie\u00dfler","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Institute of Control Systems,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Albertus Johannes","family":"Malan","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Institute of Control Systems,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00f6ren","family":"Hohmann","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Institute of Control Systems,Karlsruhe,Germany,76131"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","article-title":"Contributions to the theory of optimal control","author":"Kalman","year":"1960","journal-title":"Bol. Soc. Mat. Mex"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198537953.001.0001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.806652"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1999.832930"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3037-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1992.4792678"},{"key":"ref9","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/pbce081e"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1970.1099363"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(82)90004-8"},{"key":"ref15","article-title":"Gradient Methods for Large-Scale and Distributed Linear Quadratic Control","volume-title":"Ph.D. dissertation","author":"M\u00e5rtensson","year":"2012"},{"key":"ref16","article-title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","volume-title":"Proceedings of the 35th ICML","author":"Fazel"},{"key":"ref17","author":"Bu","year":"2019","journal-title":"LQR through the Lens of First Order Methods: Discrete-time Case"},{"key":"ref18","author":"Bu","year":"2020","journal-title":"Policy Gradient-based Algorithms for Continuous-time Linear Quadratic Control"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147853"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/361573.361582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23943\/9781400890088"},{"key":"ref24","author":"Bu","year":"2019","journal-title":"On Topological and Metrical Properties of Stabilizing Feedback Gains: the MIMO Case"},{"key":"ref25","volume-title":"Optimal Control: Linear Quadratic methods","author":"Anderson","year":"1990"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/0305004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139020411"},{"key":"ref28","volume-title":"Topology","author":"Munkres","year":"2014"},{"key":"ref29","article-title":"Old and New Matrix Algebra Useful for Statistics","author":"Minka","year":"2000"},{"key":"ref30","volume-title":"Principles of Mathematical Analysis","author":"Rudin","year":"1964"}],"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\/11312822.pdf?arnumber=11312822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:44:05Z","timestamp":1768293845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312822","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}