{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:13:11Z","timestamp":1740175991706,"version":"3.37.3"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T00:00:00Z","timestamp":1585699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"KAKENHI","award":["19K20370"],"award-info":[{"award-number":["19K20370"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2965085","type":"journal-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T20:59:18Z","timestamp":1578603558000},"page":"628-635","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Stochastic Optimization With Application to Parameter Tuning for Electronically Controlled Transmissions"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4844-6733","authenticated-orcid":false,"given":"Hiroyuki","family":"Karasawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8149-9728","authenticated-orcid":false,"given":"Tomohiro","family":"Kanemaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kei","family":"Oomae","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3940-8279","authenticated-orcid":false,"given":"Rui","family":"Fukui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"Nakao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6895-9088","authenticated-orcid":false,"given":"Takayuki","family":"Osa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref11","first-page":"1547","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref12","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref13","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","author":"parr","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2018.1509018"},{"key":"ref16","first-page":"3190","article-title":"Hierarchical relative entropy policy search","volume":"17","author":"daniel","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref17","first-page":"1607","article-title":"Relative entropy policy search","author":"peters","year":"0","journal-title":"Proc 24th AAAI Conf Artif Intell"},{"key":"ref18","first-page":"1","article-title":"Hierarchical reinforcement learning via advantage-weighted information maximization","author":"osa","year":"0","journal-title":"Proc Intl Conf on Learning Representations"},{"journal-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","year":"2006","author":"bishop","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/9781315137667"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref2","article-title":"Learning to design circuits","author":"wang","year":"0","journal-title":"Proc 32nd Annu Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"3860","article-title":"Hierarchical policy search via return-weighted density estimation","author":"osa","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"journal-title":"Optimization in the Real World Toward Solving Real-World Optimization Problems","year":"2015","author":"fujisawa","key":"ref1"},{"key":"ref20","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","author":"srinivas","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref22","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"auer","year":"2002","journal-title":"J Mach Learn Res"},{"journal-title":"Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)","year":"2006","author":"rasmussen","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2004.1430290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref26","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33206-7_8"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/08954790.pdf?arnumber=8954790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:33:00Z","timestamp":1651080780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8954790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":26,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2965085","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}