{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T01:50:03Z","timestamp":1774921803647,"version":"3.50.1"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["1808752"],"award-info":[{"award-number":["1808752"]}]},{"name":"NSF","award":["2211740"],"award-info":[{"award-number":["2211740"]}]},{"name":"NSF through a Graduate Research Fellowship","award":["026257-001"],"award-info":[{"award-number":["026257-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3392237","type":"journal-article","created":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:26:27Z","timestamp":1715361987000},"page":"6940-6954","source":"Crossref","is-referenced-by-count":4,"title":["Continuous-Time Reinforcement Learning: New Design Algorithms With Theoretical Insights and Performance Guarantees"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8145-8539","authenticated-orcid":false,"given":"Brent A.","family":"Wallace","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0374-7404","authenticated-orcid":false,"given":"Jennie","family":"Si","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref3","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"1998"},{"key":"ref4","volume-title":"A Menu of Designs for Reinforcement Learing Over Time","author":"Werbos","year":"1991"},{"key":"ref5","article-title":"Approximate dynamic programming for real-time control and neural modeling","volume-title":"Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches","author":"Werbos","year":"1992"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref7","volume-title":"Dynamic Programming and Optimal Control","author":"Bertsekas","year":"2005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2586082"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2702566"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2417510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071727"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2216523"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2014.109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2316\/p.2019.860-017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA41146.2020.9206155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.923157"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.03.089"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2431734"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2301770"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2856198"},{"issue":"1","key":"ref29","doi-asserted-by":"crossref","first-page":"19","DOI":"10.2514\/2.4870","article-title":"Apache helicopter stabilization using neural dynamic programming","volume":"25","author":"Enns","year":"2002","journal-title":"J. Guid., Control, Dyn."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.813839"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2514\/2.5107"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3122802"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591867"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2584559"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3179420"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3078317"},{"key":"ref38","first-page":"1","article-title":"Human-robotic prosthesis as collaborating agents for symmetrical walking","volume-title":"Proc. NeurIPS","volume":"36","author":"Wu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"issue":"5","key":"ref40","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.automatica.2010.02.018","article-title":"Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem","volume":"46","author":"Vamvoudakis","year":"2010","journal-title":"Automatica"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2294968"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045087"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3245980"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(87)90044-2"},{"key":"ref45","volume-title":"Modern Control Engineering","author":"Ogata","year":"1997"},{"key":"ref46","volume-title":"Analysis and Design of Multivariable Feedback Control Systems","author":"Rodriguez","year":"2004"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3145693"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2020.109421","article-title":"Policy iterations for reinforcement learning problems in continuous time and space\u2014Fundamental theory and methods","volume":"126","author":"Lee","year":"2021","journal-title":"Automatica"},{"issue":"1","key":"ref51","first-page":"9363","article-title":"Hamilton\u2013Jacobi deep Q-learning for deterministic continuous-time systems with Lipschitz continuous controls","volume":"22","author":"Kim","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3215769"},{"key":"ref53","first-page":"1","article-title":"Value iteration in continuous actions, states and time","volume-title":"Proc. 38th ICML","author":"Lutter"},{"key":"ref54","first-page":"12009","article-title":"Continuous-time model-based reinforcement learning","volume-title":"Proc. 38th ICML","author":"Yildiz"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1248"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"2686","DOI":"10.1002\/rnc.3018","article-title":"Online adaptive algorithm for optimal control with integral reinforcement learning","volume":"24","author":"Vamvoudakis","year":"2014","journal-title":"Int. J. Robust Nonlinear Control"},{"issue":"4","key":"ref57","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/s10462-017-9548-4","article-title":"Comprehensive comparison of online ADP algorithms for continuous-time optimal control","volume":"49","author":"Zhu","year":"2018","journal-title":"Artif. Intell. Rev."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2514\/2.4580"},{"issue":"1","key":"ref59","doi-asserted-by":"crossref","first-page":"58","DOI":"10.2514\/2.4197","article-title":"Design of robust control systems for a hypersonic aircraft","volume":"21","author":"Marrison","year":"1998","journal-title":"J. Guid. Control Dyn."},{"key":"ref60","article-title":"Hypersonic vehicle simulation model: Winged-cone configuration","author":"Shaughnessy","year":"1990"},{"key":"ref61","volume-title":"Flight Dynamics","author":"Stengel","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3192871"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1016\/j.neucom.2012.12.028","article-title":"Direct neural control of hypersonic flight vehicles with prediction model in discrete time","volume":"115","author":"Xu","year":"2013","journal-title":"Neurocomputing"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2456972"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2928699"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3036706"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.ast.2018.10.018","article-title":"Adaptive control for hypersonic vehicle with input saturation and state constraints","volume":"84","author":"Qiao","year":"2019","journal-title":"Aerosp. Sci. Technol."},{"issue":"16","key":"ref68","doi-asserted-by":"crossref","first-page":"8169","DOI":"10.1016\/j.jfranklin.2021.08.014","article-title":"Adaptive dynamic programing design for the neural control of hypersonic flight vehicles","volume":"358","author":"Qi","year":"2021","journal-title":"J. Franklin Inst."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2018.2887068"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2516948"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-02581-9"},{"key":"ref72","first-page":"6692","article-title":"Flight path angle dynamics of air-breathing hypersonic vehicles","volume-title":"Proc. AIAA Guid., Navigat., Control Conf. Exhib.","author":"Bolender"},{"key":"ref73","first-page":"6255","article-title":"A non-linear model for the longitudinal dynamics of a hypersonic air-breathing vehicle","volume-title":"Proc. AIAA Guid., Navigat., Control Conf. Exhib.","author":"Bolender"},{"issue":"2","key":"ref74","doi-asserted-by":"crossref","first-page":"374","DOI":"10.2514\/1.23370","article-title":"Nonlinear longitudinal dynamical model of an air-breathing hypersonic vehicle","volume":"44","author":"Bolender","year":"2007","journal-title":"J. Spacecraft Rockets"},{"key":"ref75","first-page":"1","article-title":"Decentralized control of an airbreathing scramjet-powered hypersonic vehicle","volume-title":"Proc. AIAA Guid., Navigat., Control Conf.","author":"Dickeson"},{"key":"ref76","first-page":"1","article-title":"Control-relevant modeling, analysis, and design for scramjet-powered hypersonic vehicles","volume-title":"Proc. 16th AIAA\/DLR\/DGLR Int. Space Planes Hypersonic Syst. Technol. Conf.","author":"Dickeson"},{"key":"ref77","article-title":"Control relevant modeling and design of scramjet-powered hypersonic vehicles","author":"Dickeson","year":"2012"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.2514\/6.2006-6556"},{"key":"ref79","volume-title":"Introduction to Robotics: Mechanics and Control","author":"Craig","year":"2005"},{"issue":"2","key":"ref80","first-page":"1","article-title":"Dynamic modelling of differential-drive mobile robots using Lagrange and newton-euler methodologies: A unified framework","volume":"2","author":"Dhaouadi","year":"2013","journal-title":"Adv. Robot. Autom."},{"key":"ref81","article-title":"Dynamics, directional maneuverability and optimization based multivariable control of nonholonomic differential drive mobile robots","author":"Mondal","year":"2021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICAMechS.2016.7813499"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCS.1978.1084534"},{"issue":"10","key":"ref84","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","article-title":"Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics","volume":"48","author":"Jiang","year":"2012","journal-title":"Automatica"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.2514\/6.2003-5641"},{"issue":"5","key":"ref86","doi-asserted-by":"crossref","first-page":"829","DOI":"10.2514\/1.12596","article-title":"Adaptive sliding mode control design for a hypersonic flight vehicle","volume":"27","author":"Xu","year":"2004","journal-title":"J. Guid. Control Dyn."},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2003.1213600"},{"key":"ref88","volume-title":"TNNLS 2023\u2014dEIRL","year":"2023"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1991.4791471"},{"key":"ref90","first-page":"4326","article-title":"Dynamics and control of hypersonic aeropropulsive\/aeroelastic vehicles","volume-title":"Proc. Guid., Navigat. Control Conf.","author":"Schmidt"},{"key":"ref91","first-page":"1","article-title":"An aerothermal flexible mode analysis of a hypersonic vehicle","volume":"10","author":"Williams","year":"2006","journal-title":"Air Force Res. Lab."},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.2514\/6.2008-6793"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10949581\/10528349-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10528349.pdf?arnumber=10528349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T05:46:36Z","timestamp":1743831996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10528349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":92,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3392237","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}