{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T03:28:09Z","timestamp":1776223689471,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan","award":["2021YFB2700302"],"award-info":[{"award-number":["2021YFB2700302"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172453"],"award-info":[{"award-number":["62172453"]}],"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":["61727810"],"award-info":[{"award-number":["61727810"]}],"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":["61803096"],"award-info":[{"award-number":["61803096"]}],"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":["62073086"],"award-info":[{"award-number":["62073086"]}],"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":["62076077"],"award-info":[{"award-number":["62076077"]}],"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":["U191140003"],"award-info":[{"award-number":["U191140003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2017ZT07X355"],"award-info":[{"award-number":["2017ZT07X355"]}]},{"DOI":"10.13039\/100016691","name":"Guangdong Provincial Pearl River Talents Program","doi-asserted-by":"publisher","award":["2019QN01X130"],"award-info":[{"award-number":["2019QN01X130"]}],"id":[{"id":"10.13039\/100016691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Science and Technology Program Project","award":["202002030289"],"award-info":[{"award-number":["202002030289"]}]},{"name":"Guangzhou Science and Technology Program Project","award":["6142006200403"],"award-info":[{"award-number":["6142006200403"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tcyb.2022.3157892","type":"journal-article","created":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T19:43:43Z","timestamp":1647978223000},"page":"765-778","source":"Crossref","is-referenced-by-count":29,"title":["Double Sparse Deep Reinforcement Learning via Multilayer Sparse Coding and Nonconvex Regularized Pruning"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4004-509X","authenticated-orcid":false,"given":"Haoli","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}]},{"given":"Jiqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8098-0341","authenticated-orcid":false,"given":"Zhenni","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation and the Guangdong Key Laboratory of IoT Information Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4430-7904","authenticated-orcid":false,"given":"Wuhui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7872-7718","authenticated-orcid":false,"given":"Zibin","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref32","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2950105"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2904255"},{"key":"ref36","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854997"},{"key":"ref34","first-page":"1705","article-title":"Clustering with Bregman divergences","volume":"6","author":"banerjee","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/370"},{"key":"ref11","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","author":"wang","year":"2020","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/287"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014384"},{"key":"ref14","article-title":"Learning sparse representations incrementally in deep reinforcement learning","author":"hernandez-garcia","year":"2019","journal-title":"arXiv 1912 04002"},{"key":"ref15","article-title":"Accelerated log-regularized convolutional transform learning and its convergence guarantee","author":"li","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref16","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2846226"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2924015"},{"key":"ref19","first-page":"1","article-title":"DeepHoyer: Learning sparser neural network with differentiable scale-invariant sparsity measures","author":"yang","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","author":"fan","year":"2020","journal-title":"Proc 2nd Conf Learn Dyn Control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2017.2736641"},{"key":"ref27","article-title":"Deep reinforcement learning and the deadly triad","author":"van hasselt","year":"2018","journal-title":"arXiv 1812 02648"},{"key":"ref3","article-title":"Integrated double estimator architecture for reinforcement learning","author":"lv","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"ref6","first-page":"1","article-title":"Multi-step medical image segmentation based on reinforcement learning","volume":"2020","author":"tian","year":"2020","journal-title":"J Ambient Intell Humanized Comput"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/379"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-02030-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/396"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5766"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3016644"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref1","first-page":"13504","article-title":"Promoting stochasticity for expressive policies via a simple and efficient regularization method","volume":"33","author":"zhou","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Policy distillation","author":"rusu","year":"2015","journal-title":"arXiv 1511 06295"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2967566"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.2.2.024006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-011-9289-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref25","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"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10016773\/09740040.pdf?arnumber=9740040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T23:25:29Z","timestamp":1676935529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9740040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":36,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2022.3157892","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}