{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:16:00Z","timestamp":1768338960465,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"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":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10885806","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"801-808","source":"Crossref","is-referenced-by-count":3,"title":["Asynchronous Heterogeneous Linear Quadratic Regulator Design"],"prefix":"10.1109","author":[{"given":"Leonardo F.","family":"Toso","sequence":"first","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,NY,USA,10027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Wang","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,NY,USA,10027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Anderson","sequence":"additional","affiliation":[{"name":"Columbia University,Department of Electrical Engineering,New York,NY,USA,10027"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref3","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International conference on machine learning.","author":"Fazel"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3087455"},{"key":"ref5","first-page":"2916","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume-title":"The 22nd international conference on artificial intelligence and statistics.","author":"Malik"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3037046"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/acc60939.2024.10644167"},{"key":"ref8","first-page":"1308","article-title":"Fedsysid: A federated approach to sample-efficient system identification","volume-title":"Learning for Dynamics and Control Conference.","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383950"},{"key":"ref10","article-title":"Sample-efficient linear representation learning from non-IID non-isotropic data","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10384181"},{"key":"ref12","article-title":"Model-free Learning with Heterogeneous Dynamical Systems: A Federated LQR Approach","author":"Wang","year":"2023","journal-title":"preprint arXiv:2308.11743"},{"key":"ref13","article-title":"Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for the Model-free LQR","author":"Toso","year":"2024","journal-title":"arXiv preprint arXiv:2401.14534"},{"key":"ref14","first-page":"586","article-title":"Multi-task imitation learning for linear dynamical systems","volume-title":"Learning for Dynamics and Control Conference.","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110741"},{"key":"ref16","article-title":"Fleet Policy Learning via Weight Merging and An Application to Robotic Tool-Use","author":"Wang","year":"2023","journal-title":"rXiv preprint arXiv:2310.01362"},{"key":"ref17","article-title":"Towards model-free lqr control over rate-limited channels","author":"Mitra","year":"2024","journal-title":"arXiv preprint arXiv:2401.01258"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992745"},{"key":"ref19","first-page":"3581","article-title":"Federated learning with buffered asynchronous aggregation","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Nguyen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton49937.2022.9929409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC51059.2022.9992612"},{"key":"ref22","article-title":"Distributed delayed stochastic optimization","volume":"24","author":"Agarwal","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Asynchronous stochastic convex optimization: the noise is in the noise and sgd don\u2019t care","volume":"28","author":"Chaturapruek","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"4042","article-title":"Critical parameters for scalable distributed learning with large batches and asynchronous updates","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Stich"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref26","article-title":"Csmaafl: Client scheduling and model aggregation in asynchronous federated learning","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2306.01207"},{"key":"ref27","article-title":"Stochastic approximation with delayed updates: Finite-time rates under markovian sampling","author":"Adibi","year":"2024","journal-title":"arXiv preprint arXiv:2402.11800"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1971.1099755"},{"key":"ref29","first-page":"583","article-title":"A bound for the error in the normal approximation to the distribution of a sum of dependent random variables","volume-title":"Proceedings of the Sixth Berkeley Symposium on Mathematical Statistics and Probability, Volume 2: Probability Theory","volume":"6","author":"Stein"},{"key":"ref30","first-page":"420","article-title":"Asynchronous sgd beats minibatch sgd under arbitrary delays","volume":"35","author":"Mishchenko","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","first-page":"17 202","article-title":"Sharper convergence guarantees for asynchronous sgd for distributed and federated learning","volume":"35","author":"Koloskova","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Asynchronous Heterogeneous Linear Quadratic Regulator Design","author":"Toso","year":"2024","journal-title":"arXiv preprint arXiv:2404.09061"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10885806.pdf?arnumber=10885806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:33:33Z","timestamp":1740641613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10885806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10885806","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}