{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T11:25:38Z","timestamp":1793013938154,"version":"4.5.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8793789","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"8973-8979","source":"Crossref","is-referenced-by-count":337,"title":["Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience"],"prefix":"10.1109","author":[{"given":"Yevgen","family":"Chebotar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Handa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor","family":"Makoviychuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miles","family":"Macklin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Issac","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan","family":"Ratliff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11044","article-title":"Grounded action transformation for robot learning in simulation","author":"hanna","year":"2017","journal-title":"AAAI"},{"key":"ref32","article-title":"Humanoid robots learning to walk faster: From the real world to simulation and back","author":"farchy","year":"2013","journal-title":"AAMAS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/451"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759424"},{"key":"ref37","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"CoRL"},{"key":"ref36","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref35","article-title":"Auto-encoding variational Bayes","volume":"abs 1312 6114","author":"kingma","year":"2013","journal-title":"CoRR"},{"key":"ref34","article-title":"Epopt: Learning robust neural network policies using model ensembles","volume":"abs 1610 1283","author":"rajeswaran","year":"2016","journal-title":"CoRR"},{"key":"ref10","author":"ljung","year":"1999","journal-title":"System identification – Theory for the User"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84996-513-2"},{"key":"ref12","first-page":"388","article-title":"A survey on policy search for robotics","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref13","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363481"},{"key":"ref16","article-title":"Towards adapting deep visuomotor representations from simulated to real environments","volume":"abs 1511 7111","author":"tzeng","year":"2015","journal-title":"CoRR"},{"key":"ref17","article-title":"Using simulation and domain adaptation to improve efficiency of deep robotic grasping","volume":"abs 1709 7857","author":"bousmalis","year":"2017","journal-title":"CoRR"},{"key":"ref18","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"CoRL"},{"key":"ref19","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","volume":"abs 1610 3518","author":"christiano","year":"2016","journal-title":"CoRR"},{"key":"ref28","article-title":"Reinforcement learning for pivoting task","volume":"abs 1703 472","author":"antonova","year":"2017","journal-title":"CoRR"},{"key":"ref4","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"abs 1806 10293","author":"kalashnikov","year":"2018","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SIMPAR.2018.8376268"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202141"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref29","article-title":"Asymmetric actor critic for image-based robot learning","volume":"abs 1710 6542","author":"pinto","year":"2017","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref8","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","volume":"abs 1707 2267","author":"james","year":"2017","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref9","article-title":"Learning dexterous in-hand manipulation","volume":"abs 1808 177","author":"andrychowicz","year":"2018","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830505"},{"key":"ref45","article-title":"Closing the sim-to-real loop: Adapting simulation randomization with real world experience","volume":"abs 1810 5687","author":"chebotar","year":"2018","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref42","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"NIPS"},{"key":"ref24","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","author":"muratore","year":"2018","journal-title":"CoRL"},{"key":"ref41","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.030"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2018.XIV.010","article-title":"Sim-to-real: Learning agile locomotion for quadruped robots","author":"tan","year":"2018","journal-title":"RSS"},{"key":"ref43","article-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","author":"hausman","year":"2017","journal-title":"NIPS"},{"key":"ref25","article-title":"Mutual alignment transfer learning","volume":"abs 1707 7907","author":"wulfmeier","year":"2017","journal-title":"CoRR"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08793789.pdf?arnumber=8793789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T14:10:25Z","timestamp":1664115025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793789","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}