{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T08:35:39Z","timestamp":1775205339152,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Wallenberg AI, Autonomous Systems and Software Program"},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/lra.2020.3028529","type":"journal-article","created":{"date-parts":[[2020,10,2]],"date-time":"2020-10-02T20:10:56Z","timestamp":1601669456000},"page":"1-8","source":"Crossref","is-referenced-by-count":41,"title":["Stability-Guaranteed Reinforcement Learning for Contact-Rich Manipulation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0443-7982","authenticated-orcid":false,"given":"Shahbaz Abdul","family":"Khader","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3599-440X","authenticated-orcid":false,"given":"Hang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1133-0884","authenticated-orcid":false,"given":"Pietro","family":"Falco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2965-2953","authenticated-orcid":false,"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/3516.789685"},{"key":"ref2","article-title":"Control and learning of compliant manipulation skills","author":"Kronander","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989043"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9636-y"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2833142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2996067"},{"key":"ref12","article-title":"Modeling robot discrete movements with state-varying stiffness and damping: A framework for integrated motion generation and impedance control","volume":"10","author":"Khansari-Zadeh","year":"2014","journal-title":"Proc. Robot.: Science Syst."},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4321-0","volume-title":"The Cross Entropy Method: A Unified Approach To Combinatorial Optimization, Monte-Carlo Simulation (Information Science and Statistics)","author":"Rubinstein","year":"2004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.220143"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-3615(97)00015-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509861"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5648931"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2013.54"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9528-y"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2593492"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631284"},{"key":"ref26","first-page":"512","article-title":"The cross entropy method for fast policy search","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Mannor","year":"2003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3015931"},{"key":"ref28","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Adv. Neural Inform. Process. Syst.","author":"Berkenkamp","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref30","first-page":"1141","article-title":"Control regularization for reduced variance reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Cheng","year":"2019"},{"key":"ref31","article-title":"Parameter space noise for exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Matthias","year":"2018"},{"key":"ref32","volume-title":"Applied Nonlinear Control","author":"Slotine","year":"1991"},{"key":"ref33","volume-title":"Robotics: Modelling, Planning and Control","author":"Siciliano","year":"2010"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9223766\/09211756.pdf?arnumber=9211756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:13:05Z","timestamp":1706058785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9211756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":33,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lra.2020.3028529","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}