{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T05:35:59Z","timestamp":1678340159994},"reference-count":93,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"content-version":"vor","delay-in-days":3,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-2146814, CPS-2136197, CNS-2106403, NGSDI-2105648"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Meas. Anal. Comput. Syst."],"published-print":{"date-parts":[[2023,2,27]]},"abstract":"We investigate the problem of stabilizing an unknown networked linear system under communication constraints and adversarial disturbances. We propose the first provably stabilizing algorithm for the problem. The algorithm uses a distributed version of nested convex body chasing to maintain a consistent estimate of the network dynamics and applies system level synthesis to determine a distributed controller based on this estimated model. Our approach avoids the need for system identification and accommodates a broad class of communication delay while being fully distributed and scaling favorably with the number of subsystems.<\/jats:p>","DOI":"10.1145\/3579452","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T23:50:57Z","timestamp":1677801057000},"page":"1-43","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Online Adversarial Stabilization of Unknown Networked Systems"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-1318-0189","authenticated-orcid":false,"given":"Jing","family":"Yu","sequence":"first","affiliation":[{"name":"California Institute of Technology, Pasadena, CA, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7856-985X","authenticated-orcid":false,"given":"Dimitar","family":"Ho","sequence":"additional","affiliation":[{"name":"California Institute of Technology, Pasadena, CA, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5923-0199","authenticated-orcid":false,"given":"Adam","family":"Wierman","sequence":"additional","affiliation":[{"name":"California Institute of Technology, Pasadena, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the 24th Annual Conference on Learning Theory. JMLR Workshop and Conference Proceedings, 1--26","author":"Abbasi-Yadkori Yasin","year":"2011","unstructured":"Yasin Abbasi-Yadkori and Csaba Szepesv\u00e1ri . 2011 . Regret bounds for the adaptive control of linear quadratic systems . In Proceedings of the 24th Annual Conference on Learning Theory. JMLR Workshop and Conference Proceedings, 1--26 . Yasin Abbasi-Yadkori and Csaba Szepesv\u00e1ri. 2011. Regret bounds for the adaptive control of linear quadratic systems. In Proceedings of the 24th Annual Conference on Learning Theory. JMLR Workshop and Conference Proceedings, 1--26."},{"key":"e_1_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 111--119","author":"Agarwal Naman","year":"2019","unstructured":"Naman Agarwal , Brian Bullins , Elad Hazan , Sham Kakade , and Karan Singh . 2019 . Online control with adversarial disturbances . In International Conference on Machine Learning. PMLR, 111--119 . Naman Agarwal, Brian Bullins, Elad Hazan, Sham Kakade, and Karan Singh. 2019. Online control with adversarial disturbances. In International Conference on Machine Learning. PMLR, 111--119."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2003.10.002"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814663"},{"key":"e_1_2_1_5_1","volume-title":"D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems. arXiv preprint arXiv:2103.11572","author":"Alemzadeh Siavash","year":"2021","unstructured":"Siavash Alemzadeh , Shahriar Talebi , and Mehran Mesbahi . 2021. D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems. arXiv preprint arXiv:2103.11572 ( 2021 ). Siavash Alemzadeh, Shahriar Talebi, and Mehran Mesbahi. 2021. D3PI: Data-Driven Distributed Policy Iteration for Homogeneous Interconnected Systems. arXiv preprint arXiv:2103.11572 (2021)."},{"key":"e_1_2_1_6_1","volume-title":"Data-driven Distributed and Localized Model Predictive Control. arXiv preprint arXiv:2112.12229","author":"Alonso Carmen Amo","year":"2021","unstructured":"Carmen Amo Alonso , Fengjun Yang , and Nikolai Matni . 2021. Data-driven Distributed and Localized Model Predictive Control. arXiv preprint arXiv:2112.12229 ( 2021 ). Carmen Amo Alonso, Fengjun Yang, and Nikolai Matni. 2021. Data-driven Distributed and Localized Model Predictive Control. arXiv preprint arXiv:2112.12229 (2021)."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.03.006"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262844"},{"key":"e_1_2_1_9_1","volume-title":"LATIN 2016: Theoretical Informatics","author":"Antoniadis Antonios","unstructured":"Antonios Antoniadis , Neal Barcelo , Michael Nugent , Kirk Pruhs , Kevin Schewior , and Michele Scquizzato . 2016. Chasing convex bodies and functions . In LATIN 2016: Theoretical Informatics . Springer , 68--81. Antonios Antoniadis, Neal Barcelo, Michael Nugent, Kirk Pruhs, Kevin Schewior, and Michele Scquizzato. 2016. Chasing convex bodies and functions. In LATIN 2016: Theoretical Informatics. Springer, 68--81."},{"key":"e_1_2_1_10_1","volume-title":"Chasing Convex Bodies and Functions. Ph.,D. Dissertation","author":"Argue Charles","unstructured":"Charles Argue . 2022. Chasing Convex Bodies and Functions. Ph.,D. Dissertation . Carnegie Mellon University . Charles Argue. 2022. Chasing Convex Bodies and Functions. Ph.,D. Dissertation. Carnegie Mellon University."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3310435.3310443"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450349"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00065-X"},{"key":"e_1_2_1_15_1","volume-title":"Predictive control for linear and hybrid systems","author":"Borrelli Francesco","unstructured":"Francesco Borrelli , Alberto Bemporad , and Manfred Morari . 2017. Predictive control for linear and hybrid systems . Cambridge University Press . Francesco Borrelli, Alberto Bemporad, and Manfred Morari. 2017. Predictive control for linear and hybrid systems. Cambridge University Press."},{"key":"e_1_2_1_16_1","volume-title":"LQR through the lens of first order methods: Discrete-time case. arXiv preprint arXiv:1907.08921","author":"Bu Jingjing","year":"2019","unstructured":"Jingjing Bu , Afshin Mesbahi , Maryam Fazel , and Mehran Mesbahi . 2019. LQR through the lens of first order methods: Discrete-time case. arXiv preprint arXiv:1907.08921 ( 2019 ). Jingjing Bu, Afshin Mesbahi, Maryam Fazel, and Mehran Mesbahi. 2019. LQR through the lens of first order methods: Discrete-time case. arXiv preprint arXiv:1907.08921 (2019)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975994.91"},{"key":"e_1_2_1_18_1","volume-title":"Conference on Learning Theory. PMLR, 1114--1143","author":"Chen Xinyi","year":"2021","unstructured":"Xinyi Chen and Elad Hazan . 2021 . Black-box control for linear dynamical systems . In Conference on Learning Theory. PMLR, 1114--1143 . Xinyi Chen and Elad Hazan. 2021. Black-box control for linear dynamical systems. In Conference on Learning Theory. PMLR, 1114--1143."},{"key":"e_1_2_1_19_1","volume-title":"Conference on Learning Theory. PMLR, 867--908","author":"Christianson Nicolas","year":"2022","unstructured":"Nicolas Christianson , Tinashe Handina , and Adam Wierman . 2022 . Chasing convex bodies and functions with black-box advice . In Conference on Learning Theory. PMLR, 867--908 . Nicolas Christianson, Tinashe Handina, and Adam Wierman. 2022. Chasing convex bodies and functions with black-box advice. In Conference on Learning Theory. PMLR, 867--908."},{"key":"e_1_2_1_20_1","volume-title":"International Conference on Machine Learning. PMLR, 1300--1309","author":"Cohen Alon","year":"2019","unstructured":"Alon Cohen , Tomer Koren , and Yishay Mansour . 2019 . Learning Linear-Quadratic Regulators Efficiently with only sqrt(T) Regret . In International Conference on Machine Learning. PMLR, 1300--1309 . Alon Cohen, Tomer Koren, and Yishay Mansour. 2019. Learning Linear-Quadratic Regulators Efficiently with only sqrt(T) Regret. In International Conference on Machine Learning. PMLR, 1300--1309."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"key":"e_1_2_1_22_1","unstructured":"Sarah Dean Nikolai Matni Benjamin Recht and Vickie Ye. 2020b. Robust guarantees for perception-based control. In Learning for Dynamics and Control. PMLR 350--360. Sarah Dean Nikolai Matni Benjamin Recht and Vickie Ye. 2020b. Robust guarantees for perception-based control. In Learning for Dynamics and Control. PMLR 350--360."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814865"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3177780"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3290-0"},{"key":"e_1_2_1_26_1","volume-title":"Smart grid-The new and improved power grid: A survey","author":"Fang Xi","year":"2011","unstructured":"Xi Fang , Satyajayant Misra , Guoliang Xue , and Dejun Yang . 2011. Smart grid-The new and improved power grid: A survey . IEEE communications surveys & tutorials, Vol. 14 , 4 ( 2011 ), 944--980. Xi Fang, Satyajayant Misra, Guoliang Xue, and Dejun Yang. 2011. Smart grid-The new and improved power grid: A survey. IEEE communications surveys & tutorials, Vol. 14, 4 (2011), 944--980."},{"key":"e_1_2_1_27_1","volume-title":"Joint Learning-Based Stabilization of Multiple Unknown Linear Systems. arXiv preprint arXiv:2201.01387","author":"Shirani Faradonbeh Mohamad Kazem","year":"2022","unstructured":"Mohamad Kazem Shirani Faradonbeh and Aditya Modi . 2022. Joint Learning-Based Stabilization of Multiple Unknown Linear Systems. arXiv preprint arXiv:2201.01387 ( 2022 ). Mohamad Kazem Shirani Faradonbeh and Aditya Modi. 2022. Joint Learning-Based Stabilization of Multiple Unknown Linear Systems. arXiv preprint arXiv:2201.01387 (2022)."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2883241"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2998952"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2014.6859120"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1291108"},{"key":"e_1_2_1_32_1","unstructured":"Luca Furieri Yang Zheng and Maryam Kamgarpour. 2020. Learning the globally optimal distributed LQ regulator. In Learning for Dynamics and Control. PMLR 287--297. Luca Furieri Yang Zheng and Maryam Kamgarpour. 2020. Learning the globally optimal distributed LQ regulator. In Learning for Dynamics and Control. PMLR 287--297."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304077"},{"key":"e_1_2_1_34_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2504--2513","author":"Goel Gautam","year":"2019","unstructured":"Gautam Goel and Adam Wierman . 2019 . An online algorithm for smoothed regression and lqr control . In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2504--2513 . Gautam Goel and Adam Wierman. 2019. An online algorithm for smoothed regression and lqr control. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 2504--2513."},{"key":"e_1_2_1_35_1","volume-title":"42nd IEEE International Conference on Decision and Control (IEEE Cat. No. 03CH37475)","volume":"5","author":"Han Jeongheon","year":"2003","unstructured":"Jeongheon Han and Robert E Skelton . 2003 . An LMI optimization approach for structured linear controllers . In 42nd IEEE International Conference on Decision and Control (IEEE Cat. No. 03CH37475) , Vol. 5 . IEEE, 5143--5148. Jeongheon Han and Robert E Skelton. 2003. An LMI optimization approach for structured linear controllers. In 42nd IEEE International Conference on Decision and Control (IEEE Cat. No. 03CH37475), Vol. 5. IEEE, 5143--5148."},{"key":"e_1_2_1_36_1","unstructured":"Elad Hazan Sham Kakade and Karan Singh. 2020. The nonstochastic control problem. In Algorithmic Learning Theory. PMLR 408--421. Elad Hazan Sham Kakade and Karan Singh. 2020. The nonstochastic control problem. In Algorithmic Learning Theory. PMLR 408--421."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814896"},{"key":"e_1_2_1_38_1","volume-title":"Online Robust Control of Nonlinear Systems with Large Uncertainty. In International Conference on Artificial Intelligence and Statistics. PMLR, 3475--3483","author":"Ho Dimitar","year":"2021","unstructured":"Dimitar Ho , Hoang Le , John Doyle , and Yisong Yue . 2021 . Online Robust Control of Nonlinear Systems with Large Uncertainty. In International Conference on Artificial Intelligence and Statistics. PMLR, 3475--3483 . Dimitar Ho, Hoang Le, John Doyle, and Yisong Yue. 2021. Online Robust Control of Nonlinear Systems with Large Uncertainty. In International Conference on Artificial Intelligence and Statistics. PMLR, 3475--3483."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1972.1100016"},{"key":"e_1_2_1_40_1","volume-title":"On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory. arXiv preprint arXiv:2202.07187","author":"Hu Yang","year":"2022","unstructured":"Yang Hu , Adam Wierman , and Guannan Qu. 2022. On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory. arXiv preprint arXiv:2202.07187 ( 2022 ). Yang Hu, Adam Wierman, and Guannan Qu. 2022. On the Sample Complexity of Stabilizing LTI Systems on a Single Trajectory. arXiv preprint arXiv:2202.07187 (2022)."},{"key":"e_1_2_1_41_1","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Ibrahimi Morteza","year":"2012","unstructured":"Morteza Ibrahimi , Adel Javanmard , and Benjamin Roy . 2012 . Efficient reinforcement learning for high dimensional linear quadratic systems . Advances in Neural Information Processing Systems , Vol. 25 (2012). Morteza Ibrahimi, Adel Javanmard, and Benjamin Roy. 2012. Efficient reinforcement learning for high dimensional linear quadratic systems. Advances in Neural Information Processing Systems, Vol. 25 (2012)."},{"key":"e_1_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Petros Ioannou and Barics Fidan. 2006. Adaptive control tutorial. SIAM. Petros Ioannou and Barics Fidan. 2006. Adaptive control tutorial. SIAM.","DOI":"10.1137\/1.9780898718652"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00028-0"},{"key":"e_1_2_1_44_1","volume-title":"Learning Distributed Stabilizing Controllers for Multi-Agent Systems","author":"Jing Gangshan","year":"2021","unstructured":"Gangshan Jing , He Bai , Jemin George , Aranya Chakrabortty , and Piyush K Sharma . 2021. Learning Distributed Stabilizing Controllers for Multi-Agent Systems . IEEE Control Systems Letters ( 2021 ). Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, and Piyush K Sharma. 2021. Learning Distributed Stabilizing Controllers for Multi-Agent Systems. IEEE Control Systems Letters (2021)."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029822"},{"key":"e_1_2_1_46_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 5354--5390","author":"Lale Sahin","year":"2022","unstructured":"Sahin Lale , Kamyar Azizzadenesheli , Babak Hassibi , and Animashree Anandkumar . 2022 . Reinforcement learning with fast stabilization in linear dynamical systems . In International Conference on Artificial Intelligence and Statistics. PMLR, 5354--5390 . Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, and Animashree Anandkumar. 2022. Reinforcement learning with fast stabilization in linear dynamical systems. In International Conference on Artificial Intelligence and Statistics. PMLR, 5354--5390."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304202"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.05.010"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214126"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225700"},{"key":"e_1_2_1_51_1","volume-title":"Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees. arXiv preprint arXiv:2111.00411","author":"Li Yingying","year":"2021","unstructured":"Yingying Li , Subhro Das , Jeff Shamma , and Na Li. 2021a. Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees. arXiv preprint arXiv:2111.00411 ( 2021 ). Yingying Li, Subhro Das, Jeff Shamma, and Na Li. 2021a. Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees. arXiv preprint arXiv:2111.00411 (2021)."},{"key":"e_1_2_1_52_1","volume-title":"Distributed reinforcement learning for decentralized linear quadratic control: A derivative-free policy optimization approach","author":"Li Yingying","year":"2021","unstructured":"Yingying Li , Yujie Tang , Runyu Zhang , and Na Li. 2021b. Distributed reinforcement learning for decentralized linear quadratic control: A derivative-free policy optimization approach . IEEE Trans. Automat. Control ( 2021 ). Yingying Li, Yujie Tang, Runyu Zhang, and Na Li. 2021b. Distributed reinforcement learning for decentralized linear quadratic control: A derivative-free policy optimization approach. IEEE Trans. Automat. Control (2021)."},{"key":"e_1_2_1_53_1","volume-title":"Online Adaptive Controller Selection in Time-Varying Systems: No-Regret via Contractive Perturbations. arXiv preprint arXiv:2210.12320","author":"Lin Yiheng","year":"2022","unstructured":"Yiheng Lin , James Preiss , Emile Anand , Yingying Li , Yisong Yue , and Adam Wierman . 2022. Online Adaptive Controller Selection in Time-Varying Systems: No-Regret via Contractive Perturbations. arXiv preprint arXiv:2210.12320 ( 2022 ). Yiheng Lin, James Preiss, Emile Anand, Yingying Li, Yisong Yue, and Adam Wierman. 2022. Online Adaptive Controller Selection in Time-Varying Systems: No-Regret via Contractive Perturbations. arXiv preprint arXiv:2210.12320 (2022)."},{"key":"e_1_2_1_54_1","volume-title":"Distributed reinforcement learning in multi-agent networked systems. arXiv","author":"Lin Yiheng","year":"2020","unstructured":"Yiheng Lin , Guannan Qu , Longbo Huang , and Adam Wierman . 2020. Distributed reinforcement learning in multi-agent networked systems. arXiv ( 2020 ). Yiheng Lin, Guannan Qu, Longbo Huang, and Adam Wierman. 2020. Distributed reinforcement learning in multi-agent networked systems. arXiv (2020)."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2015.01.002"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2517570"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.2514\/1.G000218"},{"key":"e_1_2_1_58_1","volume-title":"Reinforcement Learning of Structured Stabilizing Control for Linear Systems with Unknown State Matrix","author":"Mukherjee Sayak","year":"2022","unstructured":"Sayak Mukherjee and Thanh Long Vu. 2022. Reinforcement Learning of Structured Stabilizing Control for Linear Systems with Unknown State Matrix . IEEE Trans. Automat. Control ( 2022 ). Sayak Mukherjee and Thanh Long Vu. 2022. Reinforcement Learning of Structured Stabilizing Control for Linear Systems with Unknown State Matrix. IEEE Trans. Automat. Control (2022)."},{"key":"e_1_2_1_59_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Perdomo Juan","year":"2021","unstructured":"Juan Perdomo , Jack Umenberger , and Max Simchowitz . 2021 . Stabilizing Dynamical Systems via Policy Gradient Methods . Advances in Neural Information Processing Systems , Vol. 34 (2021). Juan Perdomo, Jack Umenberger, and Max Simchowitz. 2021. Stabilizing Dynamical Systems via Policy Gradient Methods. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_2_1_60_1","volume-title":"Scalable multi-agent reinforcement learning for networked systems with average reward. arXiv preprint arXiv:2006.06626","author":"Qu Guannan","year":"2020","unstructured":"Guannan Qu , Yiheng Lin , Adam Wierman , and Na Li. 2020a. Scalable multi-agent reinforcement learning for networked systems with average reward. arXiv preprint arXiv:2006.06626 ( 2020 ). Guannan Qu, Yiheng Lin, Adam Wierman, and Na Li. 2020a. Scalable multi-agent reinforcement learning for networked systems with average reward. arXiv preprint arXiv:2006.06626 (2020)."},{"key":"e_1_2_1_61_1","unstructured":"Guannan Qu Adam Wierman and Na Li. 2020b. Scalable reinforcement learning of localized policies for multi-agent networked systems. In Learning for Dynamics and Control. PMLR 256--266. Guannan Qu Adam Wierman and Na Li. 2020b. Scalable reinforcement learning of localized policies for multi-agent networked systems. In Learning for Dynamics and Control. PMLR 256--266."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4739468"},{"key":"e_1_2_1_64_1","volume-title":"A characterization of convex problems in decentralized control","author":"Rotkowitz Michael","year":"2005","unstructured":"Michael Rotkowitz and Sanjay Lall . 2005. A characterization of convex problems in decentralized control . IEEE transactions on Automatic Control , Vol. 50 , 12 ( 2005 ), 1984--1996. Michael Rotkowitz and Sanjay Lall. 2005. A characterization of convex problems in decentralized control. IEEE transactions on Automatic Control, Vol. 50, 12 (2005), 1984--1996."},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2281881"},{"key":"e_1_2_1_66_1","first-page":"20636","article-title":"Online optimization with memory and competitive control","volume":"33","author":"Shi Guanya","year":"2020","unstructured":"Guanya Shi , Yiheng Lin , Soon-Jo Chung , Yisong Yue , and Adam Wierman . 2020 . Online optimization with memory and competitive control . Advances in Neural Information Processing Systems , Vol. 33 (2020), 20636 -- 20647 . Guanya Shi, Yiheng Lin, Soon-Jo Chung, Yisong Yue, and Adam Wierman. 2020. Online optimization with memory and competitive control. Advances in Neural Information Processing Systems, Vol. 33 (2020), 20636--20647.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2012.2233692"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3086190"},{"key":"e_1_2_1_69_1","volume-title":"International Conference on Machine Learning. PMLR, 8937--8948","author":"Simchowitz Max","year":"2020","unstructured":"Max Simchowitz and Dylan Foster . 2020 . Naive exploration is optimal for online lqr . In International Conference on Machine Learning. PMLR, 8937--8948 . Max Simchowitz and Dylan Foster. 2020. Naive exploration is optimal for online lqr. In International Conference on Machine Learning. PMLR, 8937--8948."},{"key":"e_1_2_1_70_1","volume-title":"Conference On Learning Theory. PMLR, 439--473","author":"Simchowitz Max","year":"2018","unstructured":"Max Simchowitz , Horia Mania , Stephen Tu , Michael I Jordan , and Benjamin Recht . 2018 . Learning without mixing: Towards a sharp analysis of linear system identification . In Conference On Learning Theory. PMLR, 439--473 . Max Simchowitz, Horia Mania, Stephen Tu, Michael I Jordan, and Benjamin Recht. 2018. Learning without mixing: Towards a sharp analysis of linear system identification. In Conference On Learning Theory. PMLR, 439--473."},{"key":"e_1_2_1_71_1","volume-title":"Nonlinear and optimal control theory","author":"Sontag Eduardo D","unstructured":"Eduardo D Sontag . 2008. Input to state stability: Basic concepts and results . In Nonlinear and optimal control theory . Springer , 163--220. Eduardo D Sontag. 2008. Input to state stability: Basic concepts and results. In Nonlinear and optimal control theory. Springer, 163--220."},{"key":"e_1_2_1_72_1","volume-title":"Distributed control design for heterogeneous interconnected systems","author":"Sturz Yvonne R","year":"2020","unstructured":"Yvonne R Sturz , Annika Eichler , and Roy S Smith . 2020. Distributed control design for heterogeneous interconnected systems . IEEE Trans. Automat. Control ( 2020 ). Yvonne R Sturz, Annika Eichler, and Roy S Smith. 2020. Distributed control design for heterogeneous interconnected systems. IEEE Trans. Automat. Control (2020)."},{"key":"e_1_2_1_73_1","volume-title":"Distributed Model-Free Policy Iteration for Networks of Homogeneous Systems. In 2021 60th IEEE Conference on Decision and Control (CDC). IEEE, 6970--6975","author":"Talebi Shahriar","year":"2021","unstructured":"Shahriar Talebi , Siavash Alemzadeh , and Mehran Mesbahi . 2021 a. Distributed Model-Free Policy Iteration for Networks of Homogeneous Systems. In 2021 60th IEEE Conference on Decision and Control (CDC). IEEE, 6970--6975 . Shahriar Talebi, Siavash Alemzadeh, and Mehran Mesbahi. 2021a. Distributed Model-Free Policy Iteration for Networks of Homogeneous Systems. In 2021 60th IEEE Conference on Decision and Control (CDC). IEEE, 6970--6975."},{"key":"e_1_2_1_74_1","volume-title":"On regularizability and its application to online control of unstable LTI systems","author":"Talebi Shahriar","year":"2021","unstructured":"Shahriar Talebi , Siavash Alemzadeh , Niyousha Rahimi , and Mehran Mesbahi . 2021b. On regularizability and its application to online control of unstable LTI systems . IEEE Trans. Automat. Control ( 2021 ). Shahriar Talebi, Siavash Alemzadeh, Niyousha Rahimi, and Mehran Mesbahi. 2021b. On regularizability and its application to online control of unstable LTI systems. IEEE Trans. Automat. Control (2021)."},{"key":"e_1_2_1_75_1","unstructured":"Lenart Treven Sebastian Curi Mojm'ir Mutn\u1ef3 and Andreas Krause. 2021. Learning stabilizing controllers for unstable linear quadratic regulators from a single trajectory. In Learning for Dynamics and Control. PMLR 664--676. Lenart Treven Sebastian Curi Mojm'ir Mutn\u1ef3 and Andreas Krause. 2021. Learning stabilizing controllers for unstable linear quadratic regulators from a single trajectory. In Learning for Dynamics and Control. PMLR 664--676."},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1985.1103988"},{"key":"e_1_2_1_77_1","volume-title":"Conference on Learning Theory. PMLR, 3036--3083","author":"Tu Stephen","year":"2019","unstructured":"Stephen Tu and Benjamin Recht . 2019 . The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint . In Conference on Learning Theory. PMLR, 3036--3083 . Stephen Tu and Benjamin Recht. 2019. The gap between model-based and model-free methods on the linear quadratic regulator: An asymptotic viewpoint. In Conference on Learning Theory. PMLR, 3036--3083."},{"key":"e_1_2_1_78_1","volume-title":"Sample complexity bounds for the linear quadratic regulator","author":"Stephen L Tu.","unstructured":"Stephen L Tu. 2019. Sample complexity bounds for the linear quadratic regulator . University of California , Berkeley. Stephen L Tu. 2019. Sample complexity bounds for the linear quadratic regulator. University of California, Berkeley."},{"key":"e_1_2_1_79_1","unstructured":"Jack Umenberger and Thomas B Sch\u00f6n. 2020. Optimistic robust linear quadratic dual control. In Learning for Dynamics and Control. PMLR 550--560. Jack Umenberger and Thomas B Sch\u00f6n. 2020. Optimistic robust linear quadratic dual control. In Learning for Dynamics and Control. PMLR 550--560."},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525205"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039638"},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2819246"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2890753"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01933494"},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2337838"},{"key":"e_1_2_1_86_1","volume-title":"Regret Bounds for Learning Decentralized Linear Quadratic Regulator with Partially Nested Information Structure. arXiv preprint arXiv:2210.08886","author":"Ye Lintao","year":"2022","unstructured":"Lintao Ye , Ming Chi , and Vijay Gupta . 2022. Regret Bounds for Learning Decentralized Linear Quadratic Regulator with Partially Nested Information Structure. arXiv preprint arXiv:2210.08886 ( 2022 ). Lintao Ye, Ming Chi, and Vijay Gupta. 2022. Regret Bounds for Learning Decentralized Linear Quadratic Regulator with Partially Nested Information Structure. arXiv preprint arXiv:2210.08886 (2022)."},{"key":"e_1_2_1_87_1","volume-title":"On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure. arXiv preprint arXiv:2110.07112","author":"Ye Lintao","year":"2021","unstructured":"Lintao Ye , Hao Zhu , and Vijay Gupta . 2021. On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure. arXiv preprint arXiv:2110.07112 ( 2021 ). Lintao Ye, Hao Zhu, and Vijay Gupta. 2021. On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure. arXiv preprint arXiv:2110.07112 (2021)."},{"key":"e_1_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3538637.3538853"},{"key":"e_1_2_1_89_1","volume-title":"2021 American Control Conference (ACC). IEEE, 2732--2738","author":"Yu Jing","year":"2021","unstructured":"Jing Yu , Yuh-Shyang Wang , and James Anderson . 2021 . Localized and Distributed $mathcalH_2$ State Feedback Control . In 2021 American Control Conference (ACC). IEEE, 2732--2738 . Jing Yu, Yuh-Shyang Wang, and James Anderson. 2021. Localized and Distributed $mathcalH_2$ State Feedback Control. In 2021 American Control Conference (ACC). IEEE, 2732--2738."},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2612831"},{"key":"e_1_2_1_91_1","volume-title":"Learning Stabilizing Controllers of Linear Systems via Discount Policy Gradient. arXiv preprint arXiv:2112.09294","author":"Zhao Feiran","year":"2021","unstructured":"Feiran Zhao , Xingyun Fu , and Keyou You . 2021. Learning Stabilizing Controllers of Linear Systems via Discount Policy Gradient. arXiv preprint arXiv:2112.09294 ( 2021 ). Feiran Zhao, Xingyun Fu, and Keyou You. 2021. Learning Stabilizing Controllers of Linear Systems via Discount Policy Gradient. arXiv preprint arXiv:2112.09294 (2021)."},{"key":"e_1_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2979785"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2726578"}],"container-title":["Proceedings of the ACM on Measurement and Analysis of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579452","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,8]],"date-time":"2023-03-08T23:44:01Z","timestamp":1678319041000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579452"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":93,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2,27]]}},"alternative-id":["10.1145\/3579452"],"URL":"http:\/\/dx.doi.org\/10.1145\/3579452","relation":{},"ISSN":["2476-1249"],"issn-type":[{"value":"2476-1249","type":"electronic"}],"subject":["Computer Networks and Communications","Hardware and Architecture","Safety, Risk, Reliability and Quality","Computer Science (miscellaneous)"],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-03-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}