{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:14:01Z","timestamp":1789672441965,"version":"4.0.1"},"reference-count":29,"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":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L020688\/1"],"award-info":[{"award-number":["EP\/L020688\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1109\/lra.2020.2965392","type":"journal-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T20:59:18Z","timestamp":1578603558000},"page":"683-690","source":"Crossref","is-referenced-by-count":16,"title":["Constrained-Space Optimization and Reinforcement Learning for Complex Tasks"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8037-355X","authenticated-orcid":false,"given":"Ya-Yen","family":"Tsai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9361-4340","authenticated-orcid":false,"given":"Bo","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8914-8786","authenticated-orcid":false,"given":"Edward","family":"Johns","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang-Zhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1991.131713"},{"key":"ref12","article-title":"Receptive field weighted regression","author":"schaal","year":"1997"},{"key":"ref13","first-page":"288","article-title":"Locally weighted projection regression: An o (n) algorithm for incremental real time learning in high dimensional space","volume":"1","author":"vijayakumar","year":"0","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref15","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2016","journal-title":"arXiv 1610 04286"},{"key":"ref16","volume":"2","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref17","doi-asserted-by":"crossref","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":"ref18","article-title":"Gradient-free policy architecture search and adaptation","author":"ebrahimi","year":"2017","journal-title":"arXiv 1710 05958"},{"key":"ref19","article-title":"Reinforcement learning from imperfect demonstrations","author":"gao","year":"2018","journal-title":"arXiv 1802 05313"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794292"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594133"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206355"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509621"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5627594"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2894722"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2653850"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225222"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref1","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"atkeson","year":"1997","journal-title":"Porc 15th Int Conf Adv Robot"},{"key":"ref20","first-page":"3223","article-title":"Deep Q-learning from demonstrations","author":"hester","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref21","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"ve?er\u00edk","year":"2017","journal-title":"arXiv 1707 08817"},{"key":"ref24","first-page":"2474","article-title":"Policy optimization with demonstrations","author":"kang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"2859","article-title":"Learning from limited demonstrations","author":"kim","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90005-6"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8932682\/08954748.pdf?arnumber=8954748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:32:59Z","timestamp":1651080779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8954748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":29,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.2965392","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}