{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:32:40Z","timestamp":1730255560106,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8461137","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement Learning of Depth Stabilization with a Micro Diving Agent"],"prefix":"10.1109","author":[{"given":"Gerrit","family":"Brinkmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wallace M.","family":"Bessa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel-A.","family":"Duecker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edwin","family":"Kreuzer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eugen","family":"Solowjow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2519947"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2714142"},{"key":"ref13","first-page":"4902","article-title":"Learning swing-free trajectories for UAVs with a suspended load","author":"faust","year":"2013","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/37.272779","article-title":"Learning control for underwater robotic vehicles","volume":"14","author":"yuh","year":"1994","journal-title":"IEEE Control Systems"},{"key":"ref15","article-title":"Reinforcement learning applied to the control of an autonomous underwater vehicle","author":"gaskett","year":"1999","journal-title":"Proceedings of the Australian Conference on Robotics and Automation (AuCRA)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4893-0"},{"journal-title":"Applied nonlinear control","year":"1991","author":"slotine","key":"ref17"},{"key":"ref4","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref6","first-page":"2369","article-title":"Generalized model learning for reinforcement learning on a humanoid robot","author":"hester","year":"2010","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref5","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.05.002"},{"key":"ref7","first-page":"85","article-title":"RTMBA: A real-time model-based reinforcement learning architecture for robot control","author":"hester","year":"2012","journal-title":"IEEE International Conference on Robotics and Automation (ICRA)"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","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"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2018,5,21]]},"location":"Brisbane, QLD","end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08461137.pdf?arnumber=8461137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:34:14Z","timestamp":1598232854000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8461137","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}