{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T08:57:59Z","timestamp":1768035479359,"version":"3.49.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873022"],"award-info":[{"award-number":["61873022"]}],"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":["61825305"],"award-info":[{"award-number":["61825305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","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","doi-asserted-by":"publisher","award":["XK1802-4"],"award-info":[{"award-number":["XK1802-4"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/tnnls.2020.2981377","type":"journal-article","created":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T20:03:00Z","timestamp":1587499380000},"page":"1217-1227","source":"Crossref","is-referenced-by-count":21,"title":["Actor\u2013Critic Learning Control With Regularization and Feature Selection in Policy Gradient Estimation"],"prefix":"10.1109","volume":"32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.825622"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/070698920"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref30","first-page":"457","article-title":"Of actor-critic","author":"degris","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref37","first-page":"380","article-title":"Value function approximation in reinforcement learning using the Fourier basis","author":"konidaris","year":"2011","journal-title":"Proc 25th Nat Conf Artif Intell"},{"key":"ref36","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref35","first-page":"1609","article-title":"A convergent O (n) algorithm for off-policy temporal-difference learning with linear function approximation","author":"sutton","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553442"},{"key":"ref14","first-page":"1764","article-title":"Sparse reinforcement learning via convex optimization","author":"qin","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2016.7532190"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808203"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2257618"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039530"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.2007095"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970838"},{"key":"ref4","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref27","author":"fortin","year":"1983","journal-title":"Augmented Lagrangian Methods Applications to the Numerical Solution of Boundary-Value Problems"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5229-0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1515\/9781400873173"},{"key":"ref5","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/12-AOS968"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"4448","article-title":"Online control basis selection by a regularized actor critic algorithm","author":"yuan","year":"2017","journal-title":"Proc Amer Control Conf (ACC)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref21","first-page":"2543","article-title":"Dual averaging methods for regularized stochastic learning and online optimization","volume":"11","author":"xiao","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref23","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"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1201\/b18401"},{"key":"ref25","first-page":"605","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9365681\/09075357.pdf?arnumber=9075357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:08Z","timestamp":1652194388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9075357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":37,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2981377","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}