{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:38:56Z","timestamp":1762522736431,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["ECCS 1750041","ECCS 2025732"],"award-info":[{"award-number":["ECCS 1750041","ECCS 2025732"]}]},{"name":"Innovation for Defence Excellence and Security","award":["CFPMN2-30"],"award-info":[{"award-number":["CFPMN2-30"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Control Netw. Syst."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tcns.2022.3184107","type":"journal-article","created":{"date-parts":[[2022,6,17]],"date-time":"2022-06-17T19:28:40Z","timestamp":1655494120000},"page":"2-14","source":"Crossref","is-referenced-by-count":1,"title":["Scalable Regret for Learning to Control Network-Coupled Subsystems With Unknown Dynamics"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8956-1378","authenticated-orcid":false,"given":"Sagar","family":"Sudhakara","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8125-1191","authenticated-orcid":false,"given":"Aditya","family":"Mahajan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, McGill University, Montreal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8310-7505","authenticated-orcid":false,"given":"Ashutosh","family":"Nayyar","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0556-4393","authenticated-orcid":false,"given":"Yi","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Preferred Networks America, Burlingame, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1978.1101704"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/00207178608933690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(91)90086-H"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(95)00013-M"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.07.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7403050"},{"volume-title":"Adaptive Control","year":"1994","author":"Astrom","key":"ref7"},{"key":"ref8","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Bradtke","year":"1993"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997317499"},{"key":"ref11","first-page":"1","article-title":"Regret bounds for the adaptive control of linear quadratic systems","volume-title":"Proc. Annu. Conf. Learn. Theory","author":"Abbasi-Yadkori","year":"2011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2998952"},{"key":"ref13","first-page":"1300","article-title":"Learning linear-quadratic regulators efficiently with only $\\sqrt{T}$ regret","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen","year":"2019"},{"key":"ref14","first-page":"23","article-title":"Efficient optimistic exploration in linear-quadratic regulators via lagrangian relaxation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abeille","year":"2020"},{"key":"ref15","first-page":"4192","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Dean","year":"2018"},{"key":"ref16","first-page":"10154","article-title":"Certainty equivalent control of LQR is efficient","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mania","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108950"},{"key":"ref18","first-page":"8937","article-title":"Naive exploration is optimal for online LQR","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Simchowitz"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108982"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2950156"},{"key":"ref21","first-page":"1","article-title":"Improved regret bounds for thompson sampling in linear quadratic control problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abeille","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3124259"},{"issue":"23","key":"ref23","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1023\/A:1013689704352","article-title":"Finite-time analysis of the multiarmed bandit problem","volume":"47","author":"Auer","year":"2002","journal-title":"Mach. Learn."},{"key":"ref24","first-page":"39.1","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","volume-title":"Proc. Conf. Learn. Theory","author":"Agrawal","year":"2012"},{"key":"ref25","first-page":"1692","article-title":"Distributed q-learning with state tracking for multi-agent networked control","volume-title":"Proc. AAMAS","author":"Wang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3072007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3128592"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814663"},{"article-title":"Policy gradient-based algorithms for continuous-time linear quadratic control","year":"2020","author":"Bu","key":"ref29"},{"key":"ref30","first-page":"531","article-title":"Learning the model-free linear quadratic regulator via random search","volume-title":"Proc. Learning Dyn. Control","author":"Mohammadi","year":"2020"},{"key":"ref31","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref32","article-title":"Near-optimal reinforcement learning in factored MDPs","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Osband","year":"2014"},{"key":"ref33","article-title":"Efficient reinforcement learning in factored MDPs with application to constrained RL","volume-title":"Proc. Intl. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2007.904450"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11537-007-0657-8"},{"key":"ref36","first-page":"411","article-title":"Multi type mean field reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Subramanian","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304279"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683030"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101497"},{"key":"ref40","article-title":"A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems","volume-title":"Proc. Conf. Decis. Control","author":"Gagrani","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2883241"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974263"},{"article-title":"Bayesian optimal control of smoothly parameterized systems: The lazy posterior sampling algorithm","year":"2014","author":"Abbasi-Yadkori","key":"ref43"}],"container-title":["IEEE Transactions on Control of Network Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6509490\/10075640\/9799757-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6509490\/10075640\/09799757.pdf?arnumber=9799757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:36:37Z","timestamp":1706762197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9799757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcns.2022.3184107","relation":{},"ISSN":["2325-5870","2372-2533"],"issn-type":[{"type":"electronic","value":"2325-5870"},{"type":"electronic","value":"2372-2533"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}