{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T23:08:59Z","timestamp":1725750539443},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010632","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":4,"title":["Reinforcement learning-based optimal control considering L computation time delay of linear discrete-time systems"],"prefix":"10.1109","author":[{"given":"Taishi","family":"Fujita","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toshimitu","family":"Ushio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/978-3-642-27645-3"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/MCAS.2009.933854"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ACC.1994.735224"},{"year":"2013","author":"vrabie","journal-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles","key":"ref13"},{"year":"2013","author":"lewis","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1162\/089976600300015961"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/j.automatica.2010.02.018"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-4757-2","author":"zhang","year":"2013","journal-title":"Adaptive Dynamic Programming for Control"},{"key":"ref19","article-title":"State estimation with ARMarkov models","author":"lim","year":"1998","journal-title":"Technical Report Department of Aerospace Engineering"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TAC.1985.1104007"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/IROS.2007.4399042"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/87.388130"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1007\/11552246_35"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref6"},{"year":"1995","author":"\u00e5str\u00f6m","journal-title":"Adaptive Control","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/IROS.2004.1389776"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/BF00992698"},{"year":"1989","author":"watkins","article-title":"learning from delayed rewords","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/978-3-319-01131-8"},{"year":"1996","author":"bertsekas","journal-title":"Neuro-Dynamic Programming","key":"ref9"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-85729-033-5","author":"bemporad","year":"2010","journal-title":"Networked Control Systems"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/87.826797"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TSMCB.2010.2043839"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ACC.2005.1470171"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1007\/BF00114723"},{"key":"ref23","article-title":"Q-learning-based optimal digital feedback control with computation time delay of linear discrete-time systems","author":"fujita","year":"2014","journal-title":"Proceedings of the International Symposium on Mathematical Theory of Networks and Systems"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/IROS.2005.1545025"},{"year":"1984","author":"goodwin","journal-title":"Adaptive Filtering Prediction and Control","key":"ref25"}],"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\/07010632.pdf?arnumber=7010632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T23:55:02Z","timestamp":1498175702000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010632","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}