{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T22:04:13Z","timestamp":1767650653808,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8794074","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"754-760","source":"Crossref","is-referenced-by-count":65,"title":["A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Mel","family":"Vecerik","sequence":"first","affiliation":[]},{"given":"Oleg","family":"Sushkov","sequence":"additional","affiliation":[]},{"given":"David","family":"Barker","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Rothorl","sequence":"additional","affiliation":[]},{"given":"Todd","family":"Hester","sequence":"additional","affiliation":[]},{"given":"Jon","family":"Scholz","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"A Framework for Robot Manipulation: Skill Formalism, Meta Learning and Adaptive Control","author":"johannsmeier","year":"2018","journal-title":"arXiv preprint arXiv 1805 08576"},{"key":"ref11","article-title":"Pves: Position-velocity encoders for unsupervised learning of structured state representations","author":"jonschkowski","year":"2017","journal-title":"arXiv preprint arXiv 1705 09805"},{"key":"ref12","article-title":"Task transfer via collaborative manipulation for insertion assembly","author":"kronander","year":"2014","journal-title":"Workshop on Human-Robot Interaction for Industrial Manufacturing Robotics Science and Systems"},{"key":"ref13","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17 1","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593894"},{"key":"ref16","article-title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","author":"matas","year":"2018","journal-title":"arXiv preprint arXiv 1806 07851"},{"key":"ref17","article-title":"Overcoming exploration in reinforcement learning with demonstrations","author":"nair","year":"2017","journal-title":"arXiv preprint arXiv 1709 10119"},{"key":"ref18","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2016","journal-title":"arXiv preprint arXiv 1610 01292"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.351117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"ref8","article-title":"Deep Q-learning From Demonstrations","author":"hester","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.220143"},{"key":"ref2","first-page":"449","article-title":"A Distributional Perspective on Reinforcement Learning","author":"bellemare","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning ICML 2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CYBConf.2017.7985811"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref20","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017","journal-title":"arXiv preprint arXiv 1707 08817"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/s17092004"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2019,5,20]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08794074.pdf?arnumber=8794074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:36Z","timestamp":1657854636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794074","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}