{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T11:27:05Z","timestamp":1782818825182,"version":"3.54.5"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2014,5,1]],"date-time":"2014-05-01T00:00:00Z","timestamp":1398902400000},"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. Contr. Syst. Technol."],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1109\/tcst.2013.2271276","type":"journal-article","created":{"date-parts":[[2013,8,22]],"date-time":"2013-08-22T19:15:53Z","timestamp":1377198953000},"page":"1078-1087","source":"Crossref","is-referenced-by-count":72,"title":["Self-Learning Cruise Control Using Kernel-Based Least Squares Policy Iteration"],"prefix":"10.1109","volume":"22","author":[{"family":"Jian Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Xin Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Daxue Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Zhenping Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Qingyang Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2172628"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2043839"},{"key":"ref30","author":"ma","year":"2010","journal-title":"Convergence analysis of kernel-based on-policy approximate policy iteration algorithms for Markov decision processes with continuous multidimensional states and actions"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1863","DOI":"10.1109\/TNN.2011.2168422","article-title":"Hierarchical approximate policy iteration with binary-tree state space decomposition","volume":"22","author":"xu","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"Hierarchical reinforcement learning with the MAXQ value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"J Artif Intell Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-011-0641-3"},{"key":"ref34","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"greensmith","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.08.169"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.853698"},{"key":"ref12","author":"ng","year":"2008","journal-title":"Reinforcement Learning of Dynamic Collaborative Driving"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2011.2157145"},{"key":"ref14","article-title":"Full-range adaptive cruise control based on supervised adaptive dynamic programming","author":"zhao","year":"2013","journal-title":"Neurocomputing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094892"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-010-0581-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon gradient-based policy search","volume":"15","author":"baxter","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-012-1157-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2011.2135859"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-011-9032-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20253"},{"key":"ref6","first-page":"36","article-title":"Longitudinal control design and experiment for heavy-duty trucks","author":"lu","year":"0","journal-title":"Proc Amer Control Conf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2011.0322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/87.852914"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2006.886432"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20260"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/87.974344"},{"key":"ref1","author":"anderson","year":"2008","journal-title":"Splined Speed Control Using SpAM (Speed-based Acceleration Maps) for an Autonomous Ground Vehicle"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","article-title":"Efficient reinforcement learning using recursive least-squares methods","volume":"16","author":"xu","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2098866"},{"key":"ref23","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2009.2029569"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-012-9050-9"}],"container-title":["IEEE Transactions on Control Systems Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/87\/6800075\/06584761.pdf?arnumber=6584761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:11Z","timestamp":1642004231000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6584761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5]]},"references-count":37,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcst.2013.2271276","relation":{},"ISSN":["1063-6536","1558-0865"],"issn-type":[{"value":"1063-6536","type":"print"},{"value":"1558-0865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,5]]}}}