{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T08:32:41Z","timestamp":1775809961809,"version":"3.50.1"},"reference-count":38,"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\/OAPA.html"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/lra.2019.2899918","type":"journal-article","created":{"date-parts":[[2019,2,19]],"date-time":"2019-02-19T00:23:34Z","timestamp":1550535814000},"page":"2007-2014","source":"Crossref","is-referenced-by-count":168,"title":["Learning Navigation Behaviors End-to-End With AutoRL"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5418-6371","authenticated-orcid":false,"given":"Hao-Tien Lewis","family":"Chiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3268-8685","authenticated-orcid":false,"given":"Aleksandra","family":"Faust","sequence":"additional","affiliation":[]},{"given":"Marek","family":"Fiser","sequence":"additional","affiliation":[]},{"given":"Anthony","family":"Francis","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","article-title":"Learning to reinforcement learn","author":"wang","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.10.015"},{"key":"ref30","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"0","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/700"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4655"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref34","first-page":"2902","article-title":"Large-scale evolution of image classifiers","author":"real","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.asoc.2015.11.030","article-title":"Supervised fuzzy reinforcement learning for robot navigation","volume":"40","author":"fathinezhad","year":"2016","journal-title":"Appl Soft Comput"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487169"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref13","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"0","journal-title":"Proc 1st Conf Robot Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/100.580977"},{"key":"ref15","first-page":"185","article-title":"Intention-net: Integrating planning and deep learning for goal-directed autonomous navigation","author":"gao","year":"0","journal-title":"Proc 1st Conf Robot Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"ref17","first-page":"1311","article-title":"Automated curriculum learning for neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"57","article-title":"On the adaptation of arbitrary normal mutation distributions in evolution strategies: The generating set adaptation","author":"hansen","year":"0","journal-title":"Proc Int Conf Genetic Algorithms"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.4282"},{"key":"ref28","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":"ref4","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref27","article-title":"Fetch & freight: Standard platforms for service robot applications","author":"wise","year":"0","journal-title":"Proc Workshop Auton Mobile Service Robots Int Joint Conf Artif Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2323247"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2016.2624754","article-title":"Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age","volume":"32","author":"cadena","year":"2016","journal-title":"IEEE Trans Robot"},{"key":"ref29","article-title":"Visual representations for semantic target driven navigation","author":"mousavian","year":"2018","journal-title":"CoRR"},{"key":"ref5","first-page":"227","article-title":"Hierarchical reinforcement learning for robot navigation","author":"bischoff","year":"0","journal-title":"Proc Eur Symp Artif Neural Netw"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139511"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref2","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref9","first-page":"1","article-title":"Safety, challenges, and performance of motion planners in dynamic environments","author":"chiang","year":"0","journal-title":"Proc Int Symp Robot Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3906\/elk-1311-129"},{"key":"ref20","article-title":"Barc: Backward reachability curriculum for robotic reinforcement learning","author":"ivanovic","year":"2018","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref21","first-page":"1890","article-title":"Imitation learning with demonstrations and shaping rewards","author":"judah","year":"0","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500106"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509725"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8581687\/08643443.pdf?arnumber=8643443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T06:38:44Z","timestamp":1643265524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8643443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2019.2899918","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4]]}}}