{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T02:52:11Z","timestamp":1725763931913},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867863","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T16:24:10Z","timestamp":1662395050000},"page":"4901-4908","source":"Crossref","is-referenced-by-count":3,"title":["Data-Driven Control of Markov Jump Systems: Sample Complexity and Regret Bounds"],"prefix":"10.23919","author":[{"given":"Zhe","family":"Du","sequence":"first","affiliation":[{"name":"University of Michigan,Department of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahya","family":"Sattar","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical and Computer Engineering,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davoud Ataee","family":"Tarzanagh","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laura","family":"Balzano","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Necmiye","family":"Ozay","sequence":"additional","affiliation":[{"name":"University of Michigan,Department of Electrical Engineering and Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samet","family":"Oymak","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical and Computer Engineering,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Certainty equivalent quadratic control for markov jump systems","year":"2021","author":"du","key":"ref33"},{"key":"ref32","first-page":"210","author":"vershynin","year":"2012","journal-title":"Introduction to the Non-Asymptotic Analysis of Random Matrices"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2956737"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref34","article-title":"Logarithmic regret bound in partially observable linear dynamical systems","author":"lale","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/00207178608933459"},{"journal-title":"Discrete-Time Markov Jump Linear Systems","year":"2006","author":"costa","key":"ref11"},{"key":"ref12","first-page":"282","article-title":"Combining stochastic and greedy search in hybrid estimation","author":"blackmore","year":"2005","journal-title":"AAAI"},{"key":"ref13","article-title":"Stochastic optimal control of jumping markov parameter processes with applications to finance","author":"cajueiro","year":"2002","journal-title":"Ph D dissertation PhD thesis 2002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/31.55036"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.20955\/r.90.275-294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/00207170500105384"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012992238679"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2001.v1.n2.a5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814438"},{"key":"ref4","first-page":"23","article-title":"Efficient optimistic exploration in linear-quadratic regulators via lagrangian relaxation","author":"abeille","year":"2020","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304362"},{"key":"ref3","first-page":"1","article-title":"Regret bounds for the adaptive´ control of linear quadratic systems","author":"abbasi-yadkori","year":"2011","journal-title":"Proc of COLT JMLR Workshop and Conference Proceedings"},{"key":"ref6","first-page":"1","article-title":"On the sample complexity of the linear quadratic regulator","author":"dean","year":"2019","journal-title":"FoCM"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139626514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997317499"},{"article-title":"Explore more and improve regret in linear quadratic regulators","year":"2020","author":"lale","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108982"},{"key":"ref2","article-title":"Identification and adaptive control of markov jump systems: Sample complexity and regret bounds","author":"sattar","year":"2021","journal-title":"ICML Workshop on Theoretical Foundations of Reinforcement Learning"},{"key":"ref9","article-title":"Certainty equivalence is efficient for linear quadratic control","author":"mania","year":"2019","journal-title":"NeurIPS"},{"article-title":"Identification and adaptive control of markov jump systems: Sample complexity and regret bounds","year":"2021","author":"sattar","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029946"},{"key":"ref22","first-page":"2645","article-title":"Efficient reinforcement learning for high dimensional linear quadratic systems","author":"ibrahimi","year":"2012","journal-title":"NIPS"},{"key":"ref21","first-page":"947","article-title":"Policy learning of mdps with mixed continuous\/discrete variables: A case study on model-free control of markovian jump systems","author":"jansch-porto","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref24","first-page":"4188","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","author":"dean","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"1","article-title":"Improved regret bounds for thompson sampling in linear quadratic control problems","author":"abeille","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref26","first-page":"8937","article-title":"Naive exploration is optimal for online lqr","author":"simchowitz","year":"2020","journal-title":"ICML"},{"key":"ref25","first-page":"1300","article-title":"Learning linear-quadratic regulators efficiently with only $\\sqrt T$ regret","author":"cohen","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867863.pdf?arnumber=9867863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T16:39:01Z","timestamp":1664815141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":34,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867863","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}