{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:19:31Z","timestamp":1777501171058,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793864","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"263-269","source":"Crossref","is-referenced-by-count":40,"title":["Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Biped"],"prefix":"10.1109","author":[{"given":"Tianyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hartmut","family":"Geyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher G.","family":"Atkeson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshara","family":"Rai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref12","article-title":"Sim-toreal transfer of robotic control with dynamics randomization","author":"peng","year":"2017","journal-title":"arXiv preprint arXiv 1710 06537"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref14","article-title":"Learning Dexterous In-Hand Manipulation","author":"andrychowicz","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140085"},{"key":"ref16","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"arXiv preprint arXiv 1709 10119"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref18","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Learning from demonstrations for real world reinforcement learning","author":"sendonaris","year":"2017","journal-title":"arXiv preprint arXiv 1704 03732"},{"key":"ref4","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref6","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv preprint arXiv 1707 01280"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref8","first-page":"6550","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref1","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":"ref9","first-page":"47","article-title":"Deep kernels for optimizing locomotion controllers","author":"antonova","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref20","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MEX.1986.4307016"},{"key":"ref21","article-title":"Bayesian optimization using domain knowledge on the atrias biped","author":"rai","year":"2017","journal-title":"arXiv preprint arXiv 1709 04396"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916648388"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942911"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793864.pdf?arnumber=8793864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:08:09Z","timestamp":1657854489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793864","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}