{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:16:49Z","timestamp":1780640209885,"version":"3.54.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968201","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1010-1017","source":"Crossref","is-referenced-by-count":142,"title":["Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks"],"prefix":"10.1109","author":[{"given":"Roberto","family":"Martin-Martin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle A.","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachel","family":"Gardner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2002.1258"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3099564.3099567"},{"key":"ref32","author":"ott","year":"2008","journal-title":"Cartesian Impedance Control of Redundant and Flexible-Joint Robots"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910387653"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2012.00097"},{"key":"ref36","article-title":"Learning physical collaborative robot behaviors from human demonstrations","volume":"32","author":"rozo","year":"2016","journal-title":"Transactions on Robotics"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912469821"},{"key":"ref34","volume":"42","author":"rey","year":"2018","journal-title":"Learning motions from demonstrations and rewards with timeinvariant dynamical systems based policies"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140713"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795645"},{"key":"ref15","first-page":"1651","article-title":"Adaptive human-inspired compliant contact primitives to perform surface.surface contact under uncertainty","volume":"35","author":"khansari","year":"2016","journal-title":"IJRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/027836499501400103"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TSMCB.2009.2026289","article-title":"Impedance learning for robotic contact tasks using natural actor-critic algorithm","volume":"40","author":"kim","year":"2010","journal-title":"Transactions on systems Man and Cybernetics"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139389"},{"key":"ref28","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1109\/TRO.2018.2830405","article-title":"Force, Impedance, and Trajectory Learning for Contact Tooling and Haptic Identification","volume":"34","author":"li","year":"2018","journal-title":"Transactions on Robotics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/70.508440"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648931"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1981.4308708"},{"key":"ref5","first-page":"367","article-title":"A probabilistic programming by demonstration framework handling skill constraints in joint space and task space","author":"calinon","year":"2008","journal-title":"Proc IEEE\/RSJ Intl Conf on Intelligent Robots and Systems (IROS)"},{"key":"ref8","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1812 02588"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","article-title":"Adapt: Zero-shot adaptive policy transfer for stochastic dynamical systems","author":"harrison","year":"2017","journal-title":"ISRR SPRINGER STAR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.07.008"},{"key":"ref46","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"ve?er\u00edk","year":"2017","journal-title":"arXiv preprint arXiv 1707 08817"},{"key":"ref20","article-title":"Compliant motion programming: The task frame formalism revisited","author":"kr\u00f6ger","year":"2004","journal-title":"Journal of Robotics & Mechatronics"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.044"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138997"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2861466"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2013.54"},{"key":"ref42","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref24","article-title":"Robotic agents representing, reasoning, and executing wiping tasks for daily household chores","author":"leidner","year":"2016","journal-title":"AAMAS"},{"key":"ref41","article-title":"Automating multiple-throw multilateral surgical suturing with a mechanical needle guide and sequential convex optimization","author":"sen","year":"2016","journal-title":"ICRA"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref44","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"JMLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907861"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref25","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"JMLR"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968201.pdf?arnumber=8968201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T11:10:47Z","timestamp":1658142647000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968201\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968201","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}