{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:14:11Z","timestamp":1730225651774,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/humanoids.2018.8625003","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T21:51:38Z","timestamp":1548366698000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Learning Deep Robot Controllers by Exploiting Successful and Failed Executions"],"prefix":"10.1109","author":[{"given":"Domingo","family":"Esteban","sequence":"first","affiliation":[]},{"given":"Leonel","family":"Rozo","sequence":"additional","affiliation":[]},{"given":"Darwin G.","family":"Caldwell","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref12","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"0","journal-title":"NIPS 2014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907424"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0161-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7030007"},{"key":"ref17","first-page":"1060","article-title":"Inverse reinforcement learning from failure","author":"shiarlis","year":"2016","journal-title":"AAMAS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487168"},{"key":"ref19","first-page":"1607","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.052"},{"key":"ref8","article-title":"Dual REPS: A generalization of relative entropy policy search exploiting bad experiences","author":"colome","year":"0","journal-title":"IEEE Transactions on Robotics 2017"},{"key":"ref7","article-title":"Guided policy search as approximate mirror descent","author":"montgomery","year":"0","journal-title":"NIPS 2016"},{"key":"ref2","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"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":"10.1162\/NECO_a_00393"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989383"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref23","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"chebotar","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"}],"event":{"name":"2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2018,11,6]]},"location":"Beijing, China","end":{"date-parts":[[2018,11,9]]}},"container-title":["2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8596719\/8624912\/08625003.pdf?arnumber=8625003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:49:05Z","timestamp":1643219345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8625003\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2018.8625003","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}