{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:06:20Z","timestamp":1760709980185,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1109\/cec.2019.8789935","type":"proceedings-article","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T20:00:07Z","timestamp":1565294407000},"page":"1922-1928","source":"Crossref","is-referenced-by-count":6,"title":["Memetic Evolution Strategy for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xinghua","family":"Qu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqing","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70807-0_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2009.03.005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78295-7_4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2494596"},{"key":"ref11","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv preprint arXiv 1703 04529"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/197"},{"key":"ref13","article-title":"Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"such","year":"2017","journal-title":"arXiv preprint arXiv 1712 06567"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2003.1299414"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2010.936309"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2008.2009460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.819944"},{"key":"ref18","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":"ref19","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"wierstra","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref28","volume":"65","author":"spall","year":"2005","journal-title":"Introduction to Stochastic Search and Optimization Estimation Simulation and Control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref27","volume":"37","author":"floudas","year":"2013","journal-title":"Deterministic Global Optimization Theory Methods and Applications"},{"key":"ref3","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-008-0357-1"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref8","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.12.2936"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref20","article-title":"Parameter space noise for exploration","author":"plappert","year":"2017","journal-title":"arXiv preprint arXiv 1706 01905"},{"key":"ref22","first-page":"1989","article-title":"On evolution, search, optimization, genetic algorithms and martial arts: Towards memetic algorithms","volume":"826","author":"moscato","year":"1989","journal-title":"Caltech Concurrent Computation Program C3P Report"},{"journal-title":"The Selfish Gene","year":"2017","author":"davis","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2016.7744191"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.10.009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.883272"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2016.7505399"}],"event":{"name":"2019 IEEE Congress on Evolutionary Computation (CEC)","start":{"date-parts":[[2019,6,10]]},"location":"Wellington, New Zealand","end":{"date-parts":[[2019,6,13]]}},"container-title":["2019 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8778428\/8789744\/08789935.pdf?arnumber=8789935","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:48:37Z","timestamp":1658141317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8789935\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cec.2019.8789935","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}