{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:09:39Z","timestamp":1775851779228,"version":"3.50.1"},"reference-count":107,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1563921"],"award-info":[{"award-number":["1563921"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1808752"],"award-info":[{"award-number":["1808752"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2211740"],"award-info":[{"award-number":["2211740"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF through the Graduate Research Fellowship","doi-asserted-by":"publisher","award":["026257-001"],"award-info":[{"award-number":["026257-001"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tnnls.2023.3245980","type":"journal-article","created":{"date-parts":[[2023,2,28]],"date-time":"2023-02-28T18:52:00Z","timestamp":1677610320000},"page":"10199-10219","source":"Crossref","is-referenced-by-count":18,"title":["Continuous-Time Reinforcement Learning Control: A Review of Theoretical Results, Insights on Performance, and Needs for New Designs"],"prefix":"10.1109","volume":"35","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","volume-title":"Dynamic Programming and Optimal Control","author":"Bertsekas","year":"2005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref8","volume-title":"Dynamic Programming and Markov Processes","author":"Howard","year":"1960"},{"key":"ref9","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1989.70114"},{"key":"ref12","volume-title":"A Menu of Designs for Reinforcement Learning Over Time","author":"Webros","year":"1991"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1115\/1.3640537"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2514\/3.21495"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/0328056"},{"key":"ref17","article-title":"Improving the closed-loop performance of nonlinear systems","author":"Beard","year":"1995"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(97)00128-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2294968"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3045087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2466191"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.883869"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2923011"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2017.03.022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2586082"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2702566"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2417510"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071727"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2216523"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354377"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref42","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref43","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8122622"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"1","key":"ref46","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2014.109"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2316\/P.2019.860-017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA41146.2020.9206155"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.923157"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.03.089"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2431734"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2014.2301770"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2856198"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2514\/2.4870"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.813839"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2514\/2.5107"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3122802"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591867"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2584559"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3179420"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3078317"},{"key":"ref66","first-page":"1","article-title":"Humanrobotic prosthesis as collaborating agents for symmetrical walking","volume":"36","author":"Wu","year":"2022","journal-title":"NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9548-4"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3042876"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2712188"},{"key":"ref70","article-title":"Stability guarantees for continuous RL control","author":"Song","year":"2022","journal-title":"arXiv:2209.07324"},{"issue":"1","key":"ref71","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":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109421"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3215769"},{"key":"ref74","first-page":"12009","article-title":"Continuous-time modelbased reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Yildiz"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2761852"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2785801"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.3018"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.848292"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1249-y"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2019.8865177"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3100269"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2249668"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-014-0613-7"},{"key":"ref85","volume-title":"Analysis and Design of Feedback Control Systems","author":"Rodriguez","year":"2003"},{"key":"ref86","volume-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0006368"},{"key":"ref88","volume-title":"Network Analysis and Feedback Amplifier Design","author":"Bode","year":"1945"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1932.tb02344.x"},{"key":"ref90","volume-title":"Robust Adaptive Control","author":"Ioannou","year":"1995"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1002\/9780470059579"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/BF01211469"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2396645"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2523878"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053037"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000204"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.03.005"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108672"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110581"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref102","volume-title":"Software Related to Funded Research of F.L. Lewis","year":"2022"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927523"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1142\/1192"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718027"},{"key":"ref106","volume-title":"TNNLS 2022\u2014CT-RL Optimal Control","year":"2022"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1115\/1.3426465"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10623582\/10054488-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10623582\/10054488.pdf?arnumber=10054488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T18:14:42Z","timestamp":1722968082000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10054488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":107,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3245980","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}