{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T09:01:26Z","timestamp":1767085286636,"version":"3.37.3"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017YFB1300200","2017YFB1300203"],"award-info":[{"award-number":["2017YFB1300200","2017YFB1300203"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91648205","61627808","61702516"],"award-info":[{"award-number":["91648205","61627808","61702516"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Strategic Priority Research Program of Chinese Academy of Science","doi-asserted-by":"publisher","award":["XDB32050100"],"award-info":[{"award-number":["XDB32050100"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Development of Science and Technology of Guangdong Province Special Fund Project","award":["2016B090910001"],"award-info":[{"award-number":["2016B090910001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1109\/tsmc.2019.2933152","type":"journal-article","created":{"date-parts":[[2019,10,18]],"date-time":"2019-10-18T19:54:10Z","timestamp":1571428450000},"page":"4624-4638","source":"Crossref","is-referenced-by-count":20,"title":["Connecting Model-Based and Model-Free Control With Emotion Modulation in Learning Systems"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5670-028X","authenticated-orcid":false,"given":"Xiao","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0748-4952","authenticated-orcid":false,"given":"Wei","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6384-3687","authenticated-orcid":false,"given":"Hong","family":"Qiao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0979-09.2009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1312011110"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2015.00332"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-9568.2008.06422.x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2011.02.009"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2010.04.036"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00702-017-1738-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4415-08.2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nn2007"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/npp.2014.211"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1101\/lm.81004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00262.2009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1919"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-neuro-071013-014119"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn.2017.35"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2792542"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2843563"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-017-5666-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2012.00079"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0028-3908(98)00033-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-9568.2007.05353.x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1037\/bne0000116"},{"key":"ref50","article-title":"Guide actor–critic for continuous control","author":"tangkaratt","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref51","article-title":"Model based value estimation for efficient model free reinforcement learning","author":"feinberg","year":"2018","journal-title":"CoRR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2869375"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1888"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1952.sp004764"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2013.00101"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1101\/lm.1938011"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5772\/67834"},{"key":"ref53","first-page":"5518","article-title":"Iterative linearized control: Stable algorithms and complexity guarantees","author":"roulet","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref10","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2805379"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2648"},{"key":"ref12","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2800040"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"ref16","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"Proc ICINCO (1)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2018.12.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nn1560"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2749978"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2476706"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2712188"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.12.069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2712561"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref49","first-page":"565","article-title":"Model-free trajectory-based policy optimization with monotonic improvement","volume":"19","author":"akrour","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn (ICML)"},{"key":"ref46","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614995"},{"key":"ref47","article-title":"Plan online, learn offline: Efficient learning and exploration via model based control","author":"lowrey","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent (ICLR)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.09.036"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/nn.2904"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsycho.2006.01.007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.11.028"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/9488261\/08876861.pdf?arnumber=8876861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:05Z","timestamp":1652194385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8876861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":61,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2019.2933152","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"type":"print","value":"2168-2216"},{"type":"electronic","value":"2168-2232"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}