{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:18:13Z","timestamp":1740169093642,"version":"3.37.3"},"reference-count":19,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672190","61370162"],"award-info":[{"award-number":["61672190","61370162"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2913001","type":"journal-article","created":{"date-parts":[[2019,4,24]],"date-time":"2019-04-24T20:13:57Z","timestamp":1556136837000},"page":"55763-55769","source":"Crossref","is-referenced-by-count":1,"title":["Optimistic Sampling Strategy for Data-Efficient Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6110-9219","authenticated-orcid":false,"given":"Dongfang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiafeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dansong","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianglong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Self-imitation learning","year":"2018","author":"oh","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41550-017-0321-z"},{"key":"ref12","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","author":"nachum","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.future.2018.04.050","article-title":"Multi-threaded learning control mechanism for neural networks","volume":"87","author":"po?ap","year":"2018","journal-title":"Future Gener Comput Syst"},{"key":"ref14","first-page":"2402","article-title":"Meta-gradient reinforcement learning","author":"xu","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"journal-title":"Gaussian Processes for Machine Learning","year":"2006","author":"rasmussen","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/18.30996"},{"article-title":"Asynchronous methods for deep reinforcement learning","year":"2016","author":"mnih","key":"ref18"},{"key":"ref19","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn"},{"article-title":"Self-supervised visual planning with temporal skip connections","year":"2017","author":"ebert","key":"ref4"},{"key":"ref3","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref6","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"article-title":"Neural network dynamics models for control of under-actuated legged millirobots","year":"2017","author":"nagabandi","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref2","first-page":"703","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"chebotar","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref1","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487172"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08698221.pdf?arnumber=8698221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T02:33:38Z","timestamp":1643164418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8698221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2913001","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}