{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:16:18Z","timestamp":1775841378709,"version":"3.50.1"},"reference-count":56,"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"}]},{"name":"Alexander von Humboldt Foundation, Germany"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tnnls.2022.3160173","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T19:43:15Z","timestamp":1648582995000},"page":"9742-9756","source":"Crossref","is-referenced-by-count":12,"title":["Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-3965","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Control and Systems Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control and Systems 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, ACT, Australia"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2803729"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-019-0804-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref9","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553426"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2494596"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04378-3"},{"key":"ref13","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref14","first-page":"5027","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Conti"},{"key":"ref15","first-page":"1194","article-title":"Evolution-guided policy gradient in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khadka"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014352"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2543238"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2010.06.019"},{"key":"ref19","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nagabandi"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2771451"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2007.913070"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref27","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2171713"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2160459"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0075-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911426178"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2810447"},{"key":"ref33","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"issue":"1","key":"ref34","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"Wierstra","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952353"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794343"},{"key":"ref39","first-page":"9333","article-title":"Hardware conditioned policies for multi-robot transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref41","article-title":"Policy transfer with strategy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321876"},{"key":"ref47","first-page":"5400","article-title":"Evolved policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref48","article-title":"ES-MAML: Simple Hessian-free meta learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref49","first-page":"586","article-title":"Deep learning without poor local minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kawaguchi"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref53","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref54","first-page":"4936","article-title":"Importance weighted transfer of samples in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Tirinzoni"},{"key":"ref55","article-title":"Parameter space noise for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Plappert"},{"key":"ref56","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10336252\/09744521.pdf?arnumber=9744521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:11:58Z","timestamp":1708110718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9744521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":56,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3160173","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}