{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T10:25:37Z","timestamp":1747045537553,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"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":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683706","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T15:50:18Z","timestamp":1643730618000},"page":"5086-5091","source":"Crossref","is-referenced-by-count":3,"title":["Controlling Nonlinear Dynamical Systems with Linear Quadratic Regulator-based Policy Networks in Koopman space"],"prefix":"10.1109","author":[{"given":"Tomoharu","family":"Iwata","sequence":"first","affiliation":[]},{"given":"Yoshinobu","family":"Kawahara","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1016\/j.ifacol.2018.11.790"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.23919\/ACC.2019.8815339"},{"key":"ref30","first-page":"538","article-title":"The optimal reward baseline for gradient-based reinforcement learning","author":"weaver","year":"2001","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"year":"2017","author":"kaiser","journal-title":"Data-driven discovery of Koopman eigenfunctions for control","key":"ref10"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"year":"2004","author":"kirk","journal-title":"Optimal Control Theory An Introduction","key":"ref12"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1073\/pnas.17.5.315","article-title":"Hamiltonian systems and transformation in Hilbert space","volume":"17","author":"koopman","year":"1931","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.automatica.2018.03.046"},{"key":"ref15","volume":"1","author":"kwakernaak","year":"1972","journal-title":"Linear Optimal Control Systems"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/j.jcp.2019.108973"},{"key":"ref17","article-title":"Learning compositional Koopman operators for model-based control","author":"li","year":"2019","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/BF00277162"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1175\/1520-0469(1963)020<0130:DNF>2.0.CO;2"},{"key":"ref28","first-page":"1057","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":"ref4","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"greensmith","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1007\/BF02477753"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.4324\/9780203773895"},{"key":"ref29","first-page":"1130","article-title":"Learning Koopman invariant subspaces for dynamic mode decomposition","author":"takeishi","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TSMCC.2012.2218595"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/CDC.2018.8619727"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CDC42340.2020.9304238"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.15607\/RSS.2019.XV.060"},{"year":"2020","author":"iwata","journal-title":"Neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics","key":"ref9"},{"key":"ref1","article-title":"Forecasting sequential data using consistent Koopman autoencoders","author":"azencot","year":"2020","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1038\/s41467-018-07210-0"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-35713-9","author":"mauroy","year":"2020","journal-title":"The Koopman Operator in Systems and Control"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.23919\/ACC.2019.8814903"},{"key":"ref24","first-page":"9258","article-title":"Deep dynamical modeling and control of unsteady fluid flows","author":"morton","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s11071-005-2824-x","article-title":"Spectral properties of dynamical systems, model reduction and decompositions","volume":"41","author":"mezi?","year":"2005","journal-title":"Nonlinear Dynamics"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1137\/15M1013857"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/JRPROC.1962.288235"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683706.pdf?arnumber=9683706","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:58:04Z","timestamp":1652187484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683706\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683706","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}