{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:58:37Z","timestamp":1767085117654,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561870","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"10815-10821","source":"Crossref","is-referenced-by-count":7,"title":["Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills"],"prefix":"10.1109","author":[{"given":"Samuele","family":"Tosatto","sequence":"first","affiliation":[{"name":"Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289"}]},{"given":"Georgia","family":"Chalvatzaki","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technische Universität Darmstadt,Intelligent Autonomous Systems,Darmstadt,Germany,64289"}]}],"member":"263","reference":[{"key":"ref39","first-page":"96","article-title":"An Off-Policy Policy Gradient Theorem Using Emphatic Weightings","author":"imani","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","author":"thomas","year":"2016","journal-title":"International Conference on Machine Learning"},{"journal-title":"Monte Carlo Theory Methods and Examples","year":"2013","author":"owen","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016728"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196658"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2857921"},{"key":"ref37","first-page":"1000","article-title":"On a connection between importance sampling and the likelihood ratio policy gradient","author":"jie","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"A survey on policy search for robotics","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref35","article-title":"Learning from Scarce Experience","author":"peshkin","year":"2002","journal-title":"Int“l Conf on Machine Learning"},{"key":"ref34","article-title":"Policy Improvement for POMDPs Using Normalized Importance Sampling","author":"shelton","year":"2001","journal-title":"Conf on Uncertainty in Artificial Intelligence ser UAI’01"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2808924"},{"key":"ref40","article-title":"A Nonparametric Off-Policy Policy Gradient","author":"tosatto","year":"2020","journal-title":"Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AIStats)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.886952"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2065430"},{"key":"ref14","article-title":"Probabilistic Movement Primitives","author":"paraschos","year":"2013","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9648-7"},{"key":"ref16","first-page":"33","article-title":"Reinforcement learning to adjust robot movements to new situations","volume":"6","author":"kober","year":"2011","journal-title":"Robotics Science and Systems The MIT Press"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100841"},{"article-title":"Fast policy learning through imitation and reinforcement","year":"2018","author":"cheng","key":"ref18"},{"key":"ref19","article-title":"Policy optimization with demonstrations","author":"kang","year":"2018","journal-title":"Int“l Conf on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509336"},{"article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","year":"2019","author":"kroemer","key":"ref4"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref3","article-title":"Continuous Control with Deep Reinforcement Learning","author":"lillicrap","year":"2016","journal-title":"Int’l Conf on Learning Representations (ICLR2017)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509377"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624986"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v27i1.8546","article-title":"Data”Efficient Generalization of Robot Skills with Contextual Policy Search","author":"kupcsik","year":"2013","journal-title":"AAAI Conf on Artificial Intelligence"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"haarnoja","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152399"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139390"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920910802"},{"key":"ref46","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650243"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803340"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363570"},{"key":"ref42","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942742"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"Twenty-Fourth AAAI Conference on Artificial Intelligence"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041454"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref26","article-title":"Self-paced contextual reinforcement learning","author":"klink","year":"2020","journal-title":"Conference on Robot Learning"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICARSC.2015.43"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561870.pdf?arnumber=9561870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:51:36Z","timestamp":1673563896000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561870","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}