{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:43:59Z","timestamp":1730270639752,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981112","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T14:38:15Z","timestamp":1672065495000},"page":"6881-6887","source":"Crossref","is-referenced-by-count":2,"title":["Training Dynamic Motion Primitives using Deep Reinforcement Learning to Control a Robotic Tadpole"],"prefix":"10.1109","author":[{"given":"Imran","family":"Hameed","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Mechanical Engineering,Hong Kong,China"}]},{"given":"Xu","family":"Chao","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Mechanical Engineering,Hong Kong,China"}]},{"given":"David","family":"Navarro-Alarcon","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Mechanical Engineering,Hong Kong,China"}]},{"given":"Xingjian","family":"Jing","sequence":"additional","affiliation":[{"name":"City University of Hong Kong,Department of Mechanical Engineering,Hong Kong,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635925"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proceedings of The 32nd International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636537"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3041506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2459913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793864"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abf6354"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar3449"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2014.00023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246874"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281800"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918761569"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594476"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S1672-6529(14)60037-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.03.014"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1162\/NECO_a_00393","article-title":"Dynamical movement primitives: Learning attractor models for motor behaviors","volume":"25","author":"ijspeert","year":"2013","journal-title":"Neural Computation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.915426"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981112.pdf?arnumber=9981112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T18:00:14Z","timestamp":1701367214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981112","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}