{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:35:41Z","timestamp":1729618541031,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010629","type":"proceedings-article","created":{"date-parts":[[2015,1,20]],"date-time":"2015-01-20T02:48:03Z","timestamp":1421722083000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Model-free Q-learning over finite horizon for uncertain linear continuous-time systems"],"prefix":"10.1109","author":[{"given":"Hao","family":"Xu","sequence":"first","affiliation":[]},{"given":"S.","family":"Jagannathan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.automatica.2006.09.019","article-title":"Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control","volume":"43","author":"lewis","year":"2007","journal-title":"Automatica"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2196708"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"2850","DOI":"10.1016\/j.automatica.2012.06.008","article-title":"Integral Q-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems","volume":"48","author":"lee","year":"2012","journal-title":"Automatica"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2148","DOI":"10.1109\/TAC.2010.2051187","article-title":"Finite horizon optimal control of singularly perturbed systems: a differential Lyapunov equation approach","volume":"55","author":"nguyen","year":"2010","journal-title":"IEEE Trans on Automat Contr"},{"journal-title":"Stable Adaptive Systems","year":"2005","author":"narendra","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/81.704826"},{"key":"ref18","article-title":"Uniform continuity","author":"kuderyavtse","year":"2001","journal-title":"Encyclopedia of Mathematics"},{"journal-title":"Neural network control for nonlinear discrete-time systems","year":"2006","author":"jagannathan","key":"ref19"},{"key":"ref4","first-page":"835","article-title":"A menu of designs for reinforcement learning over time","volume":"3","author":"werbos","year":"1983","journal-title":"Journ Neur Net Contr"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"journal-title":"Adaptive Learning and Pattern Recognition Systems Theory and Applications","year":"1970","author":"mendel","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2005","author":"bertsekas","key":"ref2"},{"journal-title":"Optimal Control","year":"1995","author":"lewis","key":"ref1"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1016\/j.automatica.2012.03.007","article-title":"Stochastic optimal control of unknown linear networked control system in the presence of random delays and packet losses","volume":"48","author":"xu","year":"2012","journal-title":"Automatica"},{"journal-title":"An Introduction to Diophantine Approximation","year":"1957","author":"cassels","key":"ref20"},{"journal-title":"Nonlinear System","year":"2002","author":"khalil","key":"ref22"},{"journal-title":"Differential Geometric Control Theory","year":"1983","author":"brochett","key":"ref21"}],"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\/07010629.pdf?arnumber=7010629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T03:55:02Z","timestamp":1498190102000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010629","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}