{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:14:22Z","timestamp":1754162062223,"version":"3.41.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/robio49542.2019.8961475","type":"proceedings-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T14:49:51Z","timestamp":1579618191000},"page":"1374-1379","source":"Crossref","is-referenced-by-count":1,"title":["Influences of Neural Network Structures on an Efficient Reinforcement Learning Policy Search"],"prefix":"10.1109","author":[{"given":"Wangshu","family":"Zhu","sequence":"first","affiliation":[{"name":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China"}]},{"given":"Andre","family":"Rosendo","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"63","article-title":"Gaussian processes in machine learning","author":"rasmussen","year":"2003","journal-title":"Machine Learning Summer School"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-017-1054-2"},{"key":"ref13","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":"ref14","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"article-title":"Neural architecture search with reinforcement learning","year":"2016","author":"zoph","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87536-9_40"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03194-1_4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2920429"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.11.010"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref20","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the human out of the loop: A review of Bayesian optimization","volume":"104","author":"shahriari","year":"2015","journal-title":"Proceedings of the IEEE"},{"key":"ref21","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"wierstra","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.005"},{"key":"ref23","first-page":"3011","article-title":"Gaussian processes for machine learning (GPML) toolbox","volume":"11","author":"rasmussen","year":"2010","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2019,12,6]]},"location":"Dali, China","end":{"date-parts":[[2019,12,8]]}},"container-title":["2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8953068\/8961374\/08961475.pdf?arnumber=8961475","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T18:23:57Z","timestamp":1753813437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8961475\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/robio49542.2019.8961475","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}