{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:17:48Z","timestamp":1769919468174,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8594353","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"2062-2069","source":"Crossref","is-referenced-by-count":72,"title":["Deep Reinforcement Learning for Robotic Assembly of Mixed Deformable and Rigid Objects"],"prefix":"10.1109","author":[{"given":"Jianlan","family":"Luo","sequence":"first","affiliation":[]},{"given":"Eugen","family":"Solowjow","sequence":"additional","affiliation":[]},{"given":"Chengtao","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Juan Aparicio","family":"Ojea","sequence":"additional","affiliation":[]},{"given":"Alice M.","family":"Agogino","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref16","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.220143"},{"key":"ref19","first-page":"4008","article-title":"Guided policy search via approximate mirror descent","author":"montgomery","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref28","author":"finn","year":"2016","journal-title":"Guided policy search code implementation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600101"},{"key":"ref27","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) 2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref6","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref5","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref8","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463144"},{"key":"ref2","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","article-title":"Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics","author":"levine","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"v002t27a002","DOI":"10.1115\/DSCC2015-9703","article-title":"A learning-based framework for robot peg-hole-insertion","author":"tang","year":"2015","journal-title":"ASME 2015 Dynamic Systems and Control Conference"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref24","year":"0","journal-title":"KUKA LBR iiwa"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2016.7743375"},{"key":"ref26","author":"garage","year":"0","journal-title":"PR2 Robot Manual"},{"key":"ref25","author":"robotics","year":"0","journal-title":"Sawyer User Guide"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08594353.pdf?arnumber=8594353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T08:32:56Z","timestamp":1720945976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8594353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8594353","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}