{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:27:31Z","timestamp":1740101251501,"version":"3.37.3"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992636","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"4700-4705","source":"Crossref","is-referenced-by-count":2,"title":["Achieving Logarithmic Regret via Hints in Online Learning of Noisy LQR Systems"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Akbari","sequence":"first","affiliation":[{"name":"Queen’s University,Department of Mathematics and Statistics,Kingston,ON,Canada,K7L 3N6"}]},{"given":"Bahman","family":"Gharesifard","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical and Computer Engineering,Los Angeles,CA,USA"}]},{"given":"Tamas","family":"Linder","sequence":"additional","affiliation":[{"name":"Queen’s University,Department of Mathematics and Statistics,Kingston,ON,Canada,K7L 3N6"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cdc51059.2022.9992636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/28.502180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-012-9708-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2007.4389243"},{"issue":"10","key":"ref6","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1023\/A:1026057305653","article-title":"A linear quadratic control for discrete systems with random parameters and multiplicative noise and its application to investment portfolio optimization","volume":"64","author":"Dombrovskii","year":"2003","journal-title":"Automation and Remote Control"},{"volume-title":"Dynamic programming and optimal control: Volume I.","year":"2012","author":"Bertsekas","key":"ref7"},{"key":"ref8","volume-title":"Stochastic optimal control: the discrete-time case","volume":"5","author":"Bertsekas","year":"1996"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345697"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/0325047"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/9.58496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997317499"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2006.v6.n4.a3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations (Poster)","author":"Lillicrap","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790388"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref18","first-page":"1","article-title":"Regret bounds for the adaptive control of linear quadratic systems","volume-title":"Proceedings of the 24th Annual Conference on Learning Theory","author":"Abbasi-Yadkori"},{"key":"ref19","article-title":"Efficient reinforcement learning for high dimensional linear quadratic systems","volume":"25","author":"Ibrahimi","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Finite time analysis of optimal adaptive policies for linear-quadratic systems","year":"2017","author":"Faradonbeh","key":"ref20"},{"key":"ref21","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","volume":"31","author":"Dean","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Certainty equivalence is efficient for linear quadratic control","volume":"32","author":"Mania","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"1300","article-title":"Learning linear-quadratic regulators efficiently with only $\\sqrt T $ regret","volume-title":"International Conference on Machine Learning","author":"Cohen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262873"},{"key":"ref25","first-page":"1246","article-title":"Thompson sampling for linear-quadratic control problems","volume-title":"Artificial Intelligence and Statistics","author":"Abeille","year":"2017"},{"article-title":"Thompson sampling achieves $\\tilde O(\\sqrt T )$ regret in linear quadratic control","year":"2022","author":"Kargin","key":"ref26"},{"key":"ref27","first-page":"1029","article-title":"Online linear quadratic control","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Cohen"},{"key":"ref28","first-page":"111","article-title":"Online control with adversarial disturbances","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Agarwal"},{"key":"ref29","article-title":"Logarithmic regret for online control","volume":"32","author":"Agarwal","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"476","article-title":"Riccati updates for online linear quadratic control","volume-title":"Proceedings of the 2nd Conference on Learning for Dynamics and Control","volume":"120","author":"Akbari"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s00498-022-00323-4"},{"key":"ref32","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","volume-title":"Proceedings of the Twentieth International Conference on Machine Learning","author":"Zinkevich"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/9781680831719"},{"key":"ref34","first-page":"8937","article-title":"Naive exploration is optimal for online LQR","volume-title":"International Conference on Machine Learning","author":"Simchowitz"},{"key":"ref35","first-page":"1328","article-title":"Logarithmic regret for learning linear quadratic regulators efficiently","volume-title":"International Conference on Machine Learning","author":"Cassel"},{"key":"ref36","article-title":"Online learning with a hint","volume":"30","author":"Dekel","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.09.003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104507"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","start":{"date-parts":[[2022,12,6]]},"location":"Cancun, Mexico","end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992636.pdf?arnumber=9992636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:15:29Z","timestamp":1706789729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992636","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}