{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:15:04Z","timestamp":1781590504745,"version":"3.54.5"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnnls.2021.3137548","type":"journal-article","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T20:35:12Z","timestamp":1641933312000},"page":"7059-7073","source":"Crossref","is-referenced-by-count":13,"title":["Reinforcement Learning-Based Model-Free Controller for Feedback Stabilization of Robotic Systems"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4494-1609","authenticated-orcid":false,"given":"Rupam","family":"Singh","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-4575","authenticated-orcid":false,"given":"Bharat","family":"Bhushan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Delhi Technological University, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2929996"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3050371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2896467"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870724"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2889026"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2014.0061"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2018.08.027"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2017.07.012"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.1998.728426"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.06.016"},{"key":"ref55","article-title":"Adaptive fuzzy control for a class of MIMO underactuated systems with plant uncertainties and actuator deadzones: Design and experiments","author":"yang","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/sseke"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2869375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957722"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2924839"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800085"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2503980"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1088\/0951-7715\/21\/4\/011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1090\/surv\/062"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/296185"},{"key":"ref48","author":"kailath","year":"2000","journal-title":"Linear Estimation"},{"key":"ref47","first-page":"4192","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","author":"dean","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref42","article-title":"Online least squares estimation with self-normalized processes: An application to bandit problems","author":"abbasi-yadkori","year":"2011","journal-title":"arXiv 1102 2670"},{"key":"ref41","article-title":"Model-free linear quadratic control via reduction to expert prediction","author":"abbasi-yadkori","year":"2018","journal-title":"arXiv 1804 06021"},{"key":"ref44","article-title":"On the Kronecker product","author":"sch\u00e4cke","year":"2013"},{"key":"ref43","article-title":"Learning without mixing: Towards a sharp analysis of linear system identification","author":"simchowitz","year":"2018","journal-title":"arXiv 1802 08334"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.878720"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3182\/20050703-6-CZ-1902.02088"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2013.6739785"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3182\/20130902-3-CN-3020.00064"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TLA.2016.7459596"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2363371"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2552151"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2014.1068"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref35","first-page":"3041","article-title":"Finite-sample analysis of least-squares policy iteration","volume":"13","author":"lazaric","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref34","article-title":"Contrasting exploration in parameter and action space: A zeroth-order optimization perspective","author":"vemula","year":"2019","journal-title":"arXiv 1901 11503"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/9.956050"},{"key":"ref31","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2322116"},{"key":"ref33","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"mania","year":"2018","journal-title":"arXiv 1803 07055"},{"key":"ref32","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","author":"malik","year":"2018","journal-title":"arXiv 1812 08305"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2019.04.011"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2019.100106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"key":"ref38","author":"bertsekas","year":"2017","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2852688"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2830820"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11813"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2905215"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref26","first-page":"295","article-title":"Reinforcement learning applied to linear quadratic regulation","author":"bradtke","year":"1993","journal-title":"Proc 5th Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2963849"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.108997"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-019-09829-4"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2069"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/91.227383"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971780"},{"key":"ref66","year":"2013","journal-title":"QUANSER 2DOF Ball Balancer User Manual"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979656"},{"key":"ref65","first-page":"26","year":"2013","journal-title":"2 DOF Ball Balancer Student Workbook"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2886735"},{"key":"ref27","first-page":"1","article-title":"Combining reinforcement learning and optimal control for the control of nonlinear dynamical systems","author":"abramova","year":"2015"},{"key":"ref29","article-title":"Incremental dynamic programming for on-line adaptive optimal control","author":"bradtke","year":"1995"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2275976"},{"key":"ref62","year":"2011","journal-title":"2 DOF helicopter"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2586108"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10273172\/09677459.pdf?arnumber=9677459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:17:55Z","timestamp":1698085075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9677459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3137548","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}