{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:00:42Z","timestamp":1784822442903,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["62206098"],"award-info":[{"award-number":["62206098"]}],"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":["92267105"],"award-info":[{"award-number":["92267105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012896"],"award-info":[{"award-number":["2023A1515012896"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515130002"],"award-info":[{"award-number":["2023B1515130002"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Introduced Innovative Research and Development Team of Guangdong","award":["2023ZT10L145"],"award-info":[{"award-number":["2023ZT10L145"]}]},{"name":"Guangdong Regional Joint Foundation Key Project","award":["2022B1515120076"],"award-info":[{"award-number":["2022B1515120076"]}]},{"DOI":"10.13039\/501100018601","name":"Guangdong Special Support Plan","doi-asserted-by":"publisher","award":["2021TQ06X990"],"award-info":[{"award-number":["2021TQ06X990"]}],"id":[{"id":"10.13039\/501100018601","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016096","name":"Shenzhen Basic Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818101610023"],"award-info":[{"award-number":["JCYJ20220818101610023"]}],"id":[{"id":"10.13039\/100016096","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016096","name":"Shenzhen Basic Research Program","doi-asserted-by":"publisher","award":["KJZD20230923113800001"],"award-info":[{"award-number":["KJZD20230923113800001"]}],"id":[{"id":"10.13039\/100016096","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":[[2025,12]]},"DOI":"10.1109\/tnnls.2025.3596553","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:20Z","timestamp":1755197300000},"page":"20065-20079","source":"Crossref","is-referenced-by-count":2,"title":["Strategic Evolutionary Reinforcement Learning With Operator Selection and Experience Filter"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4512-1764","authenticated-orcid":false,"given":"Kaitong","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0950-9968","authenticated-orcid":false,"given":"Ya-Hui","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6133-407X","authenticated-orcid":false,"given":"Kejiang","family":"Ye","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Shenzhen Institutes of Advanced Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0843-5802","authenticated-orcid":false,"given":"Wei-Neng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3328643"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3172754"},{"key":"ref8","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201705"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3371250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128033"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3288042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264540"},{"key":"ref14","volume-title":"An Introduction To Genetic Algorithms","author":"Mitchell","year":"1998"},{"key":"ref15","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"Stulp","year":"2012","journal-title":"arXiv:1206.4621"},{"key":"ref16","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref17","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"Petroski Such","year":"2017","journal-title":"arXiv:1712.06567"},{"key":"ref18","first-page":"1","article-title":"Evolution-guided policy gradient in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khadka"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105937"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/math11102234"},{"key":"ref21","first-page":"4264","article-title":"Guided evolutionary strategies: Augmenting random search with surrogate gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maheswaranathan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0241-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29289"},{"key":"ref25","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","author":"Pourchot","year":"2018","journal-title":"arXiv:1810.01222"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s12293-022-00375-8"},{"key":"ref27","first-page":"1","article-title":"ERL-Re2: Efficient evolutionary reinforcement learning with shared state representation and individual policy representatio","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3233\/faia240878"},{"key":"ref29","first-page":"1","article-title":"Genetic soft updates for policy evolution in deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Marchesini"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590512"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref32","first-page":"1747","article-title":"Genetic-gated networks for deep reinforcement learning","volume":"31","author":"Chang","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref33","first-page":"1","article-title":"Evolved policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010091220143"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CEC55065.2022.9870209"},{"key":"ref36","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref37","first-page":"1317","article-title":"Guiding evolutionary strategies with off-policy actor-critic","volume-title":"Proc. AAMAS","author":"Tang"},{"key":"ref38","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2016","journal-title":"arXiv:1611.01224"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2008-12102"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91086-4_14"},{"key":"ref41","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref43","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref44","first-page":"1","article-title":"Evorainbow: Combining improvements in evolutionary reinforcement learning for policy search","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2024.3399705"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/14786451.2015.1100196"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00712-x"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11272992\/11125528.pdf?arnumber=11125528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:23Z","timestamp":1764787403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":47,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3596553","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}