{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T04:17:52Z","timestamp":1774585072890,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Luxembourg National Research Fund","award":["12571953"],"award-info":[{"award-number":["12571953"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/lra.2019.2896467","type":"journal-article","created":{"date-parts":[[2019,1,30]],"date-time":"2019-01-30T20:24:52Z","timestamp":1548879892000},"page":"1549-1556","source":"Crossref","is-referenced-by-count":45,"title":["Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9470-0643","authenticated-orcid":false,"given":"Michel","family":"Breyer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-1760","authenticated-orcid":false,"given":"Fadri","family":"Furrer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0209-5915","authenticated-orcid":false,"given":"Tonci","family":"Novkovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2760-7983","authenticated-orcid":false,"given":"Roland","family":"Siegwart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4808-0831","authenticated-orcid":false,"given":"Juan","family":"Nieto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","year":"0","journal-title":"CoRR"},{"key":"ref33","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref31","article-title":"Sim-to-real: Learning agile locomotion for quadruped robots","year":"0","journal-title":"Proc Robot Sci Syst"},{"key":"ref30","article-title":"Teacher-student curriculum learning","author":"matiisen","year":"0","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759657"},{"key":"ref36","article-title":"Using simulation and domain adaptation to improve efficiency of deep robotic grasping","year":"0","journal-title":"2018 IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref35","article-title":"Adapting deep visuomotor representations with weak pairwise constraints","year":"0","journal-title":"CoRR"},{"key":"ref34","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref10","first-page":"173","article-title":"Learning hand-eye coordination for robotic grasping with large-scale data collection","author":"levine","year":"0","journal-title":"Proc Int Symp Exp Robot"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref40","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"2016"},{"key":"ref12","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"CoRR"},{"key":"ref18","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","article-title":"Data-driven grasp synthesis—A survey","volume":"30","author":"bohg","year":"2014","journal-title":"IEEE Trans Robot"},{"key":"ref28","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"0","journal-title":"Proc 35th Int Conf Machine Learn ser Machine Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/027836499601500302"},{"key":"ref27","first-page":"325","article-title":"Curriculum learning for motor skills","author":"karpathy","year":"0","journal-title":"Proc 9th Canadian Conf Artificial Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref29","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref8","first-page":"291","article-title":"Learning a visuomotor controller for real world robotic grasping using simulated depth images","author":"viereck","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/027836498800700301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref46","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"0","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref21","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"popov","year":"0","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref42","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref23","article-title":"QT-Opt: Scalable deep reinforcement learning for vision-based robotic manipulation","year":"0","journal-title":"Proc 2nd Conf Robot Learn ser Machine Research"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref26","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"0","journal-title":"2018 IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref25","article-title":"Reinforced imitation: Sample efficient deep reinforcement learning for map-less navigation by leveraging prior demonstrations","year":"0","journal-title":"IEEE l of Robotics and Automation"},{"key":"ref43","first-page":"515","article-title":"Learning deep policies for robot bin picking by simulating robust grasping sequences","author":"mahler","year":"0","journal-title":"Proc Conf Robot Learn"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8581687\/08630008.pdf?arnumber=8630008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:04:47Z","timestamp":1657746287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8630008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2019.2896467","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}