{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:34:23Z","timestamp":1778902463843,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Unions Horizon 2020 research and innovation programme","award":["640554"],"award-info":[{"award-number":["640554"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021,4,1]]},"DOI":"10.1109\/tpami.2019.2952353","type":"journal-article","created":{"date-parts":[[2019,11,8]],"date-time":"2019-11-08T22:16:45Z","timestamp":1573251405000},"page":"1172-1183","source":"Crossref","is-referenced-by-count":47,"title":["Assessing Transferability From Simulation to Reality for Reinforcement Learning"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8600-2610","authenticated-orcid":false,"given":"Fabio","family":"Muratore","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8036-2519","authenticated-orcid":false,"given":"Michael","family":"Gienger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778810"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref33","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref32","first-page":"6553","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref31","article-title":"Quanser platforms.","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref34","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"Proc Conf Robot Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344552"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref11","first-page":"3834","article-title":"Grounded action transformation for robot learning in simulation","author":"hanna","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1029\/WR025i002p00152"},{"key":"ref13","author":"isermann","year":"2010","journal-title":"Identification of Dynamic Systems An Introduction with Applications"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-1384-8_8"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2012.2185849"},{"key":"ref18","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0720-x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1502787.1502788"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-006-0708-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref29","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.1133687"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907421"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref2","article-title":"Unlocking the potential of simulators: Design with RL in mind","author":"antonova","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1214\/ss\/1032280214","article-title":"Bootstrap confidence intervals","volume":"11","author":"diciccio and","year":"1996","journal-title":"Statistical Sci"},{"key":"ref1","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(98)00054-6"},{"key":"ref22","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","author":"matas","year":"2018","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","article-title":"Learning dexterous in-hand manipulation","year":"2018","journal-title":"ArXiv e-prints 1808 00177"},{"key":"ref25","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","author":"muratore","year":"2018","journal-title":"Proc 2nd Conf Robot Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9370031\/08894399.pdf?arnumber=8894399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:49:13Z","timestamp":1652194153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8894399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,1]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2952353","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,1]]}}}