{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:29:26Z","timestamp":1729654166071,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010614","type":"proceedings-article","created":{"date-parts":[[2015,1,19]],"date-time":"2015-01-19T21:48:03Z","timestamp":1421704083000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Theoretical analysis of a reinforcement learning based switching scheme"],"prefix":"10.1109","author":[{"given":"Ali","family":"Heydari","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511627040"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref30","first-page":"55","volume":"89","author":"rudin","year":"1976","journal-title":"Principles of Mathematical Analysis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.1000146"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-26007-0","article-title":"Adaptive Dynamic Programming for Control: Algorithms and Stability","author":"zhang","year":"2012","journal-title":"Communications and Control Engineering"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2013.07.002"},{"key":"ref17","article-title":"Optimal control of uncertain quantized linear discrete-time systems","author":"zhao","year":"2014","journal-title":"International Journal of Adaptive Control and Signal Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2314612"},{"key":"ref19","article-title":"Optimal switching and control of nonlinear switching systems using approximate dynamic programming","author":"heydari","year":"2014","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2227339"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.nahs.2010.09.002"},{"key":"ref27","first-page":"53","author":"kirk","year":"1970","journal-title":"Optimal Control Theory An Introduction"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.03.019"},{"journal-title":"Reinforcement Learning An Introduction","year":"2012","author":"sutton","key":"ref6"},{"key":"ref29","first-page":"204","author":"trench","year":"2012","journal-title":"Introduction to Real Analysis"},{"key":"ref5","article-title":"Optimization of switching instants for optimal control of linear switched systems based on genetic algorithms","volume":"2","author":"sakly","year":"2009","journal-title":"IFAC Proceedings Volumes (IFAC-PapersOnline)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2514\/3.21715"},{"key":"ref7","article-title":"Approximate dynamic programming for real-time control and neural modeling","author":"werbos","year":"1992","journal-title":"Handbook of Intelligent Control"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6314919"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/0020717021000023825"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2013.12.008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2013.01.070"},{"key":"ref21","article-title":"Optimal switching between controlled subsystems with free mode sequence","author":"heydari","year":"2014","journal-title":"Neurocomputing"},{"key":"ref24","article-title":"Finite horizon optimal control of non-linear discrete-time switched systems using adaptive dynamic programming with epsilon-error bound","author":"qin","year":"2013","journal-title":"International Journal of Systems Science"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2514\/6.2013-4635"},{"key":"ref26","first-page":"3837","article-title":"An approximate dynamic programming approach for model-free control of switched systems","author":"lu","year":"2013","journal-title":"Proceedings of the IEEE Conference on Decision and Control"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1238-1"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010614.pdf?arnumber=7010614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,19]],"date-time":"2019-08-19T17:42:36Z","timestamp":1566236556000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010614","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}