{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:30:22Z","timestamp":1778693422600,"version":"3.51.4"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Boeing Strategic University Initiative"},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Research and Development for Innovative Aerospace Leadership"},{"name":"Thrust 3 - Control Automation and Mechanization","award":["FA 8650-16-C-2642"],"award-info":[{"award-number":["FA 8650-16-C-2642"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tac.2023.3290037","type":"journal-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T17:44:58Z","timestamp":1687887898000},"page":"7740-7755","source":"Crossref","is-referenced-by-count":45,"title":["Integration of Adaptive Control and Reinforcement Learning for Real-Time Control and Learning"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4354-0459","authenticated-orcid":false,"given":"Anuradha M.","family":"Annaswamy","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9668-6101","authenticated-orcid":false,"given":"Anubhav","family":"Guha","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7730-2490","authenticated-orcid":false,"given":"Yingnan","family":"Cui","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0198-6929","authenticated-orcid":false,"given":"Sunbochen","family":"Tang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7168-8381","authenticated-orcid":false,"given":"Peter A.","family":"Fisher","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9557-0414","authenticated-orcid":false,"given":"Joseph E.","family":"Gaudio","sequence":"additional","affiliation":[{"name":"Aurora Flight Sciences, Boeing Company, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Stable Adaptive Systems","author":"Narendra","year":"2005"},{"key":"ref2","volume-title":"Robust Adaptive Control","author":"Ioannou","year":"1996"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.399905"},{"key":"ref4","volume-title":"Applied Nonlinear Control","author":"Slotine","year":"1991"},{"key":"ref5","volume-title":"Nonlinear and Adaptive Control Design","author":"Krstic","year":"1995"},{"key":"ref6","volume-title":"Adaptive Control","author":"strm","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84800-066-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(03)00105-5"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898719376","volume-title":"L1 Adaptive Control Theory: Guaranteed Robustness With Fast Adaptation","author":"Hovakimyan","year":"2010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104259"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2690138"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref13","volume-title":"Neuro-Dynamic Program.","author":"Bertsekas","year":"1996"},{"issue":"3","key":"ref14","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref15","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/9.333787"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2004.1383848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2514\/6.2018-0846"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21236\/ada276517"},{"key":"ref20","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda","year":"1999"},{"key":"ref21","first-page":"5354","article-title":"Reinforcement learning with fast stabilization in linear dynamical systems","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lale","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref23","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berkenkamp","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830505"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12107"},{"key":"ref27","article-title":"Reinforcement learning under model mismatch","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Roy","year":"2017"},{"key":"ref28","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rajeswaran","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00019-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2668380"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3000190"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2204-8_23"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/9.233152"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1115\/1.1567755"},{"key":"ref35","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate ${O}(1\/k^{2})$","volume":"27","author":"Nesterov","year":"1983","journal-title":"Sov. Math. Doklady"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"},{"issue":"153","key":"ref37","first-page":"1","article-title":"A differential equation for modeling Nesterovs accelerated gradient method: Theory and insights","volume":"17","author":"Su","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1614734113"},{"key":"ref39","article-title":"Direct Runge-Kutta discretization achieves acceleration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3002513"},{"key":"ref42","first-page":"636","article-title":"Accelerated learning with robustness to adversarial regressors","volume-title":"Proc. 3rd Conf. Learn. Dyn. Control","author":"Gaudio","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3082875"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062922-090153"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029197"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029916"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304242"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3055454"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683641"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.056"},{"key":"ref51","first-page":"4192","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dean","year":"2018"},{"key":"ref52","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","year":"2018"},{"key":"ref53","article-title":"Online algorithms and policies using adaptive and machine learning approaches","author":"Annaswamy","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/0315013"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref56","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref57","volume-title":"Riemannian Geometry","author":"Carmo","year":"2013"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/0315002"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-63519-3_5"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/72.165588"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2004.1384070"},{"key":"ref62","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-4396-3","volume-title":"Robust and Adaptive Control With Aerospace Applications","author":"Lavretsky","year":"2013"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780199219858.001.0001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24853-0"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2012.2200104"},{"key":"ref66","article-title":"Proximal policy optimization algorithms","author":"Schulman"},{"key":"ref67","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717494"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2005.1582252"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10345385\/10164143.pdf?arnumber=10164143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T01:16:13Z","timestamp":1703034973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10164143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":70,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3290037","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}