{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T01:58:59Z","timestamp":1783389539431,"version":"3.54.6"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2012,3,1]],"date-time":"2012-03-01T00:00:00Z","timestamp":1330560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst., Man, Cybern. C"],"published-print":{"date-parts":[[2012,3]]},"DOI":"10.1109\/tsmcc.2011.2106494","type":"journal-article","created":{"date-parts":[[2011,2,24]],"date-time":"2011-02-24T20:44:37Z","timestamp":1298580277000},"page":"201-212","source":"Crossref","is-referenced-by-count":208,"title":["Experience Replay for Real-Time Reinforcement Learning Control"],"prefix":"10.1109","volume":"42","author":[{"given":"Sander","family":"Adam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucian","family":"Busoniu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"528","article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","author":"sutton","year":"2008","journal-title":"Proc 24th Conf Uncertainty Artif Intell"},{"key":"ref32","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2006.246657"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015445"},{"key":"ref10","author":"ernst","year":"2003","journal-title":"Near optimal closed-loop control application to electric power systems"},{"key":"ref11","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learning Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2006.377527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.897491"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5326.704563"},{"key":"ref16","first-page":"650","article-title":"Batch reinforcement learning in a complex domain","author":"kalyanakrishnan","year":"2007","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref17","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learning Res"},{"key":"ref18","first-page":"733","article-title":"Online exploration in least-squares policy iteration","author":"li","year":"2009","journal-title":"Proc 3rd Int Joint Conf Auton Agents and MultiAgent Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref28","author":"smart","year":"2002","journal-title":"Making reinforcement learning work on real robots"},{"key":"ref4","author":"bertsekas","year":"1978","journal-title":"Stochastic Optimal Control The Discrete Time Case"},{"key":"ref27","first-page":"361","author":"singh","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref3","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"buoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators (Automation and Control Engineering)"},{"key":"ref29","first-page":"903","article-title":"Practical reinforcement learning in continuous spaces","author":"smart","year":"2000","journal-title":"Proc 17th Int Conf Mach Learning"},{"key":"ref5","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/019697299125127"},{"key":"ref7","first-page":"486","article-title":"Online least-squares policy iteration for reinforcement learning control","author":"buoniu","year":"2010","journal-title":"Proc Amer Control Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2041230"},{"key":"ref9","first-page":"3327","article-title":"Efficient experience reuse in non-Markovian environments","author":"dung","year":"2008","journal-title":"Proc Int Conf Instrum Control Inf Technol"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390240"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00114-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref23","first-page":"1595","author":"perkins","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref25","year":"0"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5326\/6151926\/05719642.pdf?arnumber=5719642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T23:46:41Z","timestamp":1633909601000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5719642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3]]},"references-count":37,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tsmcc.2011.2106494","relation":{},"ISSN":["1094-6977","1558-2442"],"issn-type":[{"value":"1094-6977","type":"print"},{"value":"1558-2442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,3]]}}}