{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:48:04Z","timestamp":1757310484231,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001691","name":"JSPS KAKENHI","doi-asserted-by":"publisher","award":["19K20375","17H01249"],"award-info":[{"award-number":["19K20375","17H01249"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1109\/tcyb.2020.2983923","type":"journal-article","created":{"date-parts":[[2020,4,22]],"date-time":"2020-04-22T20:26:04Z","timestamp":1587587164000},"page":"312-322","source":"Crossref","is-referenced-by-count":11,"title":["Path Integral Policy Improvement With Population Adaptation"],"prefix":"10.1109","volume":"52","author":[{"given":"Kosuke","family":"Yamamoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2791-9979","authenticated-orcid":false,"given":"Ryo","family":"Ariizumi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2402-5179","authenticated-orcid":false,"given":"Tomohiro","family":"Hayakawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9685-3267","authenticated-orcid":false,"given":"Fumitoshi","family":"Matsuno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TNN.1998.712192"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1038\/nature16961"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ROBOT.2002.1014237"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.neunet.2008.02.003"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TRO.2012.2210294"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1016\/j.neunet.2019.01.011"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TSMC.2017.2670643"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICRA.2017.7989385"},{"volume-title":"Multi-pass Q-networks for deep reinforcement learning with parameterised action spaces","year":"2019","author":"Bester","key":"ref9"},{"year":"2010","author":"Brochu","article-title":"A tutorial on Bayesian optimization of expensive cost functions, with application to active user modelling and hierarchical reinforcement learning","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.7551\/mitpress\/3206.001.0001"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/IROS.2011.6095076"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/IROS.2011.6095039"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICRA.2013.6630691"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/TRO.2016.2632739"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.9746\/jcmsi.11.174"},{"key":"ref17","first-page":"841","article-title":"Variational heteroscedastic Gaussian process regression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"L\u00e1zaro-Gredilla"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref19","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."},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1162\/NECO_a_00393"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/bf00992696"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.5772\/61621"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1016\/j.robot.2011.07.004"},{"key":"ref24","first-page":"1","article-title":"Path integral policy improvement with covariance matrix adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stulp"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1162\/106365601750190398"},{"key":"ref26","first-page":"1","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Barth-Maron"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1016\/j.neucom.2008.04.027"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TETCI.2019.2918509"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/INCISCOS.2018.00050"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/TNN.2007.899161"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.2478\/pjbr-2013-0003"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1162\/evco.2007.15.1.1"},{"volume-title":"Proc. SICE SI Annu. Conf.","author":"Hayakawa","article-title":"Development of autonomous distributed system for gait generation of one-leg modular robot connecting into various leg configuration and its experimental verification","key":"ref33"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/ROBOT.2007.364076"},{"volume-title":"Open Dynamics Engine","year":"2020","key":"ref35"},{"key":"ref36","first-page":"157","article-title":"Self-organized shape-optimizing strategy for single-legged modular robots to traverse unknown gap environment","volume-title":"Proc. 3rd Int. Symp. Swarm Behav. Bio Inspired Robot.","author":"Hayakawa"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1016\/S0921-8890(01)00113-0"},{"volume-title":"Importance mixing: Improving sample reuse in evolutionary policy search methods","year":"2018","author":"Pourchot","key":"ref38"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9678110\/09076255.pdf?arnumber=9076255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:27:39Z","timestamp":1704839259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9076255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2020.2983923","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"type":"print","value":"2168-2267"},{"type":"electronic","value":"2168-2275"}],"subject":[],"published":{"date-parts":[[2022,1]]}}}