{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:22:34Z","timestamp":1776183754599,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811770","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"8651-8657","source":"Crossref","is-referenced-by-count":14,"title":["Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models"],"prefix":"10.1109","author":[{"given":"Iman","family":"Nematollahi","sequence":"first","affiliation":[{"name":"University of Freiburg,Germany"}]},{"given":"Erick","family":"Rosete-Beas","sequence":"additional","affiliation":[{"name":"University of Freiburg,Germany"}]},{"given":"Adrian","family":"Rpfer","sequence":"additional","affiliation":[{"name":"University of Freiburg,Germany"}]},{"given":"Tim","family":"Welschehold","sequence":"additional","affiliation":[{"name":"University of Freiburg,Germany"}]},{"given":"Abhinav","family":"Valada","sequence":"additional","affiliation":[{"name":"University of Freiburg,Germany"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"University of Freiburg,Germany"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Residual learning from demonstration: adapting dynamic movement primitives for contact-rich insertion tasks","author":"davchev","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref38","article-title":"Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards","author":"schoettler","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794219"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197409"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref36","article-title":"Neural dynamic policies for end-to-end sensorimotor learning","author":"bahl","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196582"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref10","article-title":"Nonlinear dynamical systems as movement primitives","author":"schaal","year":"0","journal-title":"International Journal of Humanoid Robotics"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636176"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353413"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2792531"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936947"},{"key":"ref17","first-page":"927","article-title":"A physically-consistent bayesian non- parametric mixture model for dynamical system learning","author":"figueroa","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593534"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.021"},{"key":"ref28","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","volume":"29","author":"finn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"Int Conf on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197331"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","author":"finn","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341491"},{"key":"ref5","first-page":"1861","article-title":"Soft actor-critic: Off- policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Int Conf on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3003865"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461044"},{"key":"ref2","first-page":"4565","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794153"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977257"},{"key":"ref22","article-title":"Euclideanizing flows: Diffeomorphic reduction for learning stable dynamical systems","author":"rana","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2020.2980591"},{"key":"ref42","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","author":"rifai","year":"0","journal-title":"Int Conf on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00299"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9636-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341035"},{"key":"ref44","article-title":"Tacto: A fast, flexible and open-source simulator for high-resolution vision-based tactile sensors","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01546"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(88)90223-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197108"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811770.pdf?arnumber=9811770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:23Z","timestamp":1667516723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811770\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811770","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}