{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T23:52:07Z","timestamp":1772236327082,"version":"3.50.1"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["SLES-2331880"],"award-info":[{"award-number":["SLES-2331880"]}]},{"name":"CAIRFI and Presidential Fellowships"},{"name":"NSF","award":["ECCS 2144634"],"award-info":[{"award-number":["ECCS 2144634"]}]},{"name":"NSF","award":["2231350"],"award-info":[{"award-number":["2231350"]}]},{"name":"Columbia DSI"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lcsys.2025.3625957","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:06:58Z","timestamp":1761588418000},"page":"2495-2500","source":"Crossref","is-referenced-by-count":2,"title":["Policy Gradient Bounds in Multitask LQR"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3325-4416","authenticated-orcid":false,"given":"Charis","family":"Stamouli","sequence":"first","affiliation":[{"name":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8679-868X","authenticated-orcid":false,"given":"Leonardo F.","family":"Toso","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Columbia University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-7541","authenticated-orcid":false,"given":"Anastasios","family":"Tsiamis","sequence":"additional","affiliation":[{"name":"Department of Information Technology and Electrical Engineering, ETH Zürich, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9081-0637","authenticated-orcid":false,"given":"George J.","family":"Pappas","sequence":"additional","affiliation":[{"name":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2832-8396","authenticated-orcid":false,"given":"James","family":"Anderson","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Columbia University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Teh"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3029864"},{"key":"ref3","article-title":"MT-Opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021","journal-title":"arXiv:2104.08212"},{"key":"ref4","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"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2005.1582904"},{"key":"ref6","first-page":"902","article-title":"Meta-learning linear quadratic regulators: A policy gradient MAML approach for model-free LQR","volume-title":"Proc. 6th Annu. Learn. Dyn. Control Conf.","author":"Toso"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC56724.2024.10885806"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2025.3625957"},{"key":"ref9","article-title":"Model-free learning with heterogeneous dynamical systems: A federated LQR approach","author":"Wang","year":"2023","journal-title":"arXiv:2308.11743"},{"key":"ref10","article-title":"Policy gradient for LQR with domain randomization","author":"Fujinami","year":"2025","journal-title":"arXiv:2503.24371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1989.70590"},{"key":"ref12","volume-title":"Essentials of robust control","author":"Zhou","year":"1998"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S1571-0661(04)80562-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.838497"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3166\/ejc.17.568-578"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7751"},{"key":"ref17","first-page":"10","article-title":"Bisimulation metrics are optimal value functions","volume-title":"Proc. 30th Conf. Uncertainty Artif. Intell.","author":"Ferns"},{"key":"ref18","article-title":"Approximate policy iteration with bisimulation metrics","author":"Kemertas","year":"2022","journal-title":"arXiv:2202.02881"},{"key":"ref19","article-title":"Layered multirate control of constrained linear systems","author":"Stamouli","year":"2025","journal-title":"arXiv:2504.10461"},{"issue":"83","key":"ref20","first-page":"1","article-title":"CVXPY: A Python-embedded modeling language for convex optimization","volume":"17","author":"Diamond","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","volume-title":"Optimal Control: Linear Quadratic Methods","author":"Anderson","year":"2007"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020021"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7782633\/10939047\/11218898-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782633\/10939047\/11218898.pdf?arnumber=11218898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T06:41:50Z","timestamp":1762497710000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11218898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2025.3625957","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}