{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:16:34Z","timestamp":1780571794225,"version":"3.54.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"European Union Horizon 2020 project CROWDBOT","award":["779942"],"award-info":[{"award-number":["779942"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/lra.2018.2869644","type":"journal-article","created":{"date-parts":[[2018,9,13]],"date-time":"2018-09-13T21:16:03Z","timestamp":1536873363000},"page":"4423-4430","source":"Crossref","is-referenced-by-count":153,"title":["Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Mapless Navigation by Leveraging Prior Demonstrations"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0276-324X","authenticated-orcid":false,"given":"Mark","family":"Pfeiffer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1670-5211","authenticated-orcid":false,"given":"Samarth","family":"Shukla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5881-3096","authenticated-orcid":false,"given":"Matteo","family":"Turchetta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2972-6011","authenticated-orcid":false,"given":"Cesar","family":"Cadena","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Krause","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2760-7983","authenticated-orcid":false,"given":"Roland","family":"Siegwart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4808-0831","authenticated-orcid":false,"given":"Juan","family":"Nieto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-008-0014-4"},{"key":"ref32","article-title":"ROS: An open-source robot operating system","author":"quigley","year":"2009","journal-title":"Proc ICRA Workshop Open Source Softw"},{"key":"ref31","first-page":"908","article-title":"Safe model-based reinforcement learning\n with stability guarantees","author":"berkenkamp","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759329"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759328"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref14","article-title":"Deep neural network for real-time autonomous indoor navigation","author":"kim","year":"2015","journal-title":"arXiv 1511 04668"},{"key":"ref15","first-page":"1","article-title":"Multimodal deep\n autoencoders for control of a mobile robot","author":"sergeant","year":"0","journal-title":"Proc Australas Conf Robot Automat"},{"key":"ref16","first-page":"627","article-title":"A\n reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref18","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref4","first-page":"739","article-title":"Off-road obstacle avoidance through end-to-end learning","author":"muller","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094992"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref5","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement\n learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref8","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00616-6_7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651222"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref20","first-page":"149","article-title":"Hierarchical reinforcement learning for robot navigation","author":"bischoff","year":"0","journal-title":"Proc 11th Int Conf Intell Eng Syst"},{"key":"ref22","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"0","journal-title":"arXiv preprint arXiv 1611 03673"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2014.6974463"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref23","article-title":"One-shot reinforcement learning for robot\n navigation with interactive replay","volume":"abs 1711 10137","author":"bruce","year":"2017","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202312"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8386768\/08458422.pdf?arnumber=8458422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:22:41Z","timestamp":1642004561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8458422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":33,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2869644","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}