{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:18:29Z","timestamp":1768339109472,"version":"3.49.0"},"reference-count":33,"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\/cdc57313.2025.11312355","type":"proceedings-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T18:19:56Z","timestamp":1768241996000},"page":"7543-7550","source":"Crossref","is-referenced-by-count":1,"title":["Learning Stabilizing Policies via an Unstable Subspace Representation"],"prefix":"10.1109","author":[{"given":"Leonardo F.","family":"Toso","sequence":"first","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lintao","family":"Ye","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Artificial Intelligence and Automation,Wuhan,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Anderson","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020021"},{"key":"ref2","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":"ref3","first-page":"2916","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume-title":"The 22nd international conference on artificial intelligence and statistics","author":"Malik"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3037046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3087455"},{"key":"ref6","article-title":"Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\\sqrt T $ Regret","volume-title":"International Conference on Machine Learning","author":"Cassel"},{"key":"ref7","article-title":"Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach","author":"Wang","year":"2023"},{"key":"ref8","first-page":"902","article-title":"Meta-learning linear quadratic regulators: a policy gradient MAML approach for model-free LQR","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Toso"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC56724.2024.10885806"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/CDC57313.2025.11312186","article-title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","author":"Zhan","year":"2025"},{"key":"ref11","first-page":"1253","article-title":"Towards model-free lqr control over rate-limited channels","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Mitra"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006256"},{"key":"ref13","first-page":"3820","article-title":"Learning to control linear systems can be hard","volume-title":"Conference on Learning Theory","author":"Tsiamis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383487"},{"key":"ref15","first-page":"32","article-title":"Explore more and improve regret in linear quadratic regulators","volume":"31","author":"Lale","year":"2020"},{"key":"ref16","first-page":"1114","article-title":"Black-box control for linear dynamical systems","volume-title":"Conference on Learning Theory","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304202"},{"key":"ref18","first-page":"29274","article-title":"Stabilizing dynamical systems via policy gradient methods","volume":"34","author":"Perdomo","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3455508"},{"key":"ref20","first-page":"16989","article-title":"On the sample complexity of stabilizing lti systems on a single trajectory","volume":"35","author":"Hu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Learning to Stabilize Unknown LTI Systems on a Single Trajectory under Stochastic Noise","author":"Zhang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2024.117483"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref24","volume-title":"Matrix perturbation theory","author":"Stewart","year":"1990"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2020.2976389"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/0707001"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1109\/CDC57313.2025.11312355","article-title":"Learning Stabilizing Policies via an Unstable Subspace Representation","author":"Toso","year":"2025"},{"key":"ref28","first-page":"5610","article-title":"Near optimal finite time identification of arbitrary linear dynamical systems","volume-title":"International Conference on Machine Learning","author":"Sarkar"},{"key":"ref29","article-title":"Online convex optimization in the bandit setting: gradient descent without a gradient","author":"Flaxman","year":"2004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386217"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479896310536"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.56021\/9781421407944"}],"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\/11312355.pdf?arnumber=11312355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:26:04Z","timestamp":1768292764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11312355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cdc57313.2025.11312355","relation":{},"subject":[],"published":{"date-parts":[[2025,12,9]]}}}