{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:17:59Z","timestamp":1725556679891},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/roman.2018.8525631","type":"proceedings-article","created":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T23:29:37Z","timestamp":1541719777000},"page":"1087-1092","source":"Crossref","is-referenced-by-count":1,"title":["Smooth and Efficient Policy Exploration for Robot Trajectory Learning"],"prefix":"10.1109","author":[{"given":"Shidi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chee-Meng","family":"Chew","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Velusamy","family":"Subramaniam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref12","first-page":"234","article-title":"State-dependent exploration for policy gradient methods","author":"rtickstieb","year":"2008","journal-title":"Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385818"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"ref3","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759306"},{"key":"ref5","first-page":"828","article-title":"Learning policy improvements with path integrals","author":"theodorou","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64107-2_2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"}],"event":{"name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2018,8,27]]},"location":"Nanjing","end":{"date-parts":[[2018,8,31]]}},"container-title":["2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8509495\/8525500\/08525631.pdf?arnumber=8525631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:28:48Z","timestamp":1643218128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8525631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/roman.2018.8525631","relation":{},"subject":[],"published":{"date-parts":[[2018,8]]}}}