{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:43:32Z","timestamp":1772905412372,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["62006111"],"award-info":[{"award-number":["62006111"]}],"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":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council\u2019s Discovery Projects funding scheme","doi-asserted-by":"publisher","award":["DP190101566"],"award-info":[{"award-number":["DP190101566"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province of China","doi-asserted-by":"publisher","award":["BK20200330"],"award-info":[{"award-number":["BK20200330"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcyb.2022.3170485","type":"journal-article","created":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T19:46:05Z","timestamp":1652816765000},"page":"7509-7520","source":"Crossref","is-referenced-by-count":18,"title":["A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-3965","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Management and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Management and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-3559","authenticated-orcid":false,"given":"Daoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales, Canberra, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5326.983933"},{"key":"ref3","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2870983"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2830820"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2901897"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-019-0804-2"},{"key":"ref11","first-page":"348","article-title":"Experience replay for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rolnick"},{"key":"ref12","first-page":"2994","article-title":"Continual learning with deep generative replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shin"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref14","first-page":"3242","article-title":"Policy consolidation for continual reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaplanis"},{"key":"ref15","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113420"},{"key":"ref17","first-page":"4528","article-title":"Progress & compress: A scalable framework for continual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schwarz"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11091"},{"key":"ref19","first-page":"316","article-title":"PAC-inspired option discovery in lifelong reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brunskill"},{"key":"ref20","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yoon"},{"key":"ref21","article-title":"A neural Dirichlet process mixture model for task-free continual learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319733"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"issue":"3","key":"ref25","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref28","first-page":"35","article-title":"Multi-task learning for classification with Dirichlet process priors","volume":"8","author":"Xue","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","first-page":"9119","article-title":"Reconciling meta-learning and continual learning with online mixtures of tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jerfel"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952353"},{"key":"ref32","first-page":"2766","article-title":"Dynamic evaluation of neural sequence models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Krause"},{"key":"ref33","article-title":"Learning to adapt in dynamic, real-world environments through Meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Nagabandi"},{"key":"ref34","article-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019","journal-title":"arXiv:1902.10486"},{"key":"ref35","first-page":"2497","article-title":"Continual reinforcement learning with complex synapses","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaplanis"},{"key":"ref36","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lopez-Paz"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/428"},{"key":"ref40","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref43","article-title":"Policy transfer with strategy optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Yu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4401"},{"key":"ref45","first-page":"3987","article-title":"Continual learning through synaptic intelligence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zenke"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2018.00027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref50","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"Proc. Conf. Robot Learn.","volume":"78","author":"Rusu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.09.001"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"issue":"1","key":"ref53","first-page":"1303","article-title":"Stochastic variational inference","volume":"14","author":"Hoffman","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10334428\/09777250.pdf?arnumber=9777250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:56:45Z","timestamp":1705960605000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9777250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":54,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2022.3170485","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}