{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T20:54:02Z","timestamp":1771102442719,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2018,12,1]],"date-time":"2018-12-01T00:00:00Z","timestamp":1543622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573052"],"award-info":[{"award-number":["61573052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61751311"],"award-info":[{"award-number":["61751311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1564214"],"award-info":[{"award-number":["U1564214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4182045"],"award-info":[{"award-number":["4182045"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"crossref","award":["ZY1839"],"award-info":[{"award-number":["ZY1839"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/tnnls.2018.2808203","type":"journal-article","created":{"date-parts":[[2018,4,5]],"date-time":"2018-04-05T23:49:33Z","timestamp":1522972173000},"page":"5899-5909","source":"Crossref","is-referenced-by-count":14,"title":["Actor-Critic Learning Control Based on <inline-formula> <tex-math notation=\"LaTeX\">$\\ell_{2}$ <\/tex-math> <\/inline-formula>-Regularized Temporal-Difference Prediction With Gradient Correction"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5299-4858","authenticated-orcid":false,"given":"Luntong","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1610-6558","authenticated-orcid":false,"given":"Dazi","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8275-5535","authenticated-orcid":false,"given":"Tianheng","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/11596448_9"},{"key":"ref38","first-page":"6627","article-title":"Online $\\ell _{2}$ -regularized reinforcement learning via RBF neural network","author":"song","year":"2016","journal-title":"Proc 28th Chin Control Decision Conf"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2424233"},{"key":"ref31","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-015-0893-y"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1007\/978-3-642-29946-9_13","article-title":"Regularized least squares temporal difference learning with nested $\\ell _{2}$ and $\\ell _{1}$ penalization","author":"hoffman","year":"2012","journal-title":"Proc 9th Eur Conf Recent Adv Reinforcement Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160611"},{"key":"ref34","first-page":"441","article-title":"Regularized policy iteration","author":"farahmand","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2236354"},{"key":"ref40","first-page":"1","article-title":"Reinforcement learning for humanoid robotics","author":"peters","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2168538"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2281663"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499757"},{"key":"ref14","article-title":"Output tracking control based on adaptive dynamic programming with multistep policy evaluation","author":"luo","year":"0","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TSMCB.2009.2026289","article-title":"Impedance learning for robotic contact tasks using natural actor-critic algorithm","volume":"40","author":"kim","year":"2010","journal-title":"IEEE Trans Syst Man Cybern B Cybern"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2772162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0142331216645176"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2316\/Journal.206.2015.2.206-4185"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref27","first-page":"289","article-title":"Off-policy learning with eligibility traces: A survey","volume":"15","author":"geist","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref6","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2623859"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2399020"},{"key":"ref2","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2329942"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesv\u00e1ri","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref46","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2003.814834"},{"key":"ref45","first-page":"1609","article-title":"A convergent O(n) temporal-difference algorithm for off-policy learning with linear function approximation","author":"sutton","year":"2009","journal-title":"Proc Conf Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2526615"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2005.846001"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/0959651815603910"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2009.374"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1613\/jair.946"},{"key":"ref23","first-page":"1169","article-title":"Natural actor-critic for road traffic optimisation","author":"richter","year":"2007","journal-title":"Proc 20th Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref43","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COEC.2003.1210269"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8540478\/08331904.pdf?arnumber=8331904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,18]],"date-time":"2022-08-18T05:02:27Z","timestamp":1660798947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8331904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":46,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2808203","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}