{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:29:27Z","timestamp":1775665767764,"version":"3.50.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004830","name":"Siemens","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004830","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004675","name":"Autodesk","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004675","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002418","name":"Intel","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010477","name":"Intuitive Surgical","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010477","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,23]]},"DOI":"10.1109\/case49439.2021.9551469","type":"proceedings-article","created":{"date-parts":[[2021,10,7]],"date-time":"2021-10-07T20:53:51Z","timestamp":1633640031000},"page":"502-509","source":"Crossref","is-referenced-by-count":24,"title":["LazyDAgger: Reducing Context Switching in Interactive Imitation Learning"],"prefix":"10.1109","author":[{"given":"Ryan","family":"Hoque","sequence":"first","affiliation":[]},{"given":"Ashwin","family":"Balakrishna","sequence":"additional","affiliation":[]},{"given":"Carl","family":"Putterman","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Daniel S.","family":"Brown","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Seita","sequence":"additional","affiliation":[]},{"given":"Brijen","family":"Thananjeyan","sequence":"additional","affiliation":[]},{"given":"Ellen","family":"Novoseller","sequence":"additional","affiliation":[]},{"given":"Ken","family":"Goldberg","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref2","article-title":"Interactive teaching strategies for agent training","volume-title":"Proc. of the International Joint Conference on Artificial Intelligence (IJCAI)","author":"Amir","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref5","article-title":"On-policy robot imitation learning from a converging supervisor","volume-title":"Conference on Robot Learning (CoRL)","author":"Balakrishna"},{"key":"ref6","volume-title":"Performance evaluation of imitation learning algorithms with human experts","author":"B\u00e5venstrand","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.29007\/b8zr"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/41.103436"},{"key":"ref9","article-title":"Better-than-demonstrator imitation learning via automaticaly-ranked demonstrations","volume-title":"Conference on Robot Learning (CoRL)","author":"Brown","year":"2019"},{"key":"ref10","article-title":"Safe imitation learning via fast bayesian reward inference from preferences","volume-title":"International Conference on Machine Learning","author":"Brown","year":"2020"},{"key":"ref11","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","author":"Brown","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2013.2293535"},{"key":"ref13","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Christiano","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2005.850587"},{"key":"ref15","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2017","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","volume-title":"Proc. Int. Conf. on Machine Learning","author":"Fujimoto","year":"2018"},{"key":"ref17","article-title":"Generative adversarial imitation learning","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.034"},{"key":"ref19","article-title":"Reward learning from human preferences and demonstrations in atari","volume-title":"Advances in Neural Information Processing Systems","author":"Ibarz","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref21","article-title":"Interactive imitation learning in state-space","author":"Jauhri","year":"2020","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Active imitation learning via state queries","volume-title":"Proceedings of the icml workshop on combining learning strategies to reduce label cost","author":"Judah"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3060404"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref25","article-title":"Active attention-modified policy shaping: Socially interactive agents track","volume-title":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems","author":"Faulkner","year":"2019"},{"key":"ref26","article-title":"Ac-teach: A bayesian actor-critic method for policy learning with an ensemble of suboptimal teachers","volume-title":"Conf. on Robot Learning (CoRL)","author":"Kurenkov","year":"2019"},{"key":"ref27","article-title":"Dart: Noise injection for robust imitation learning","volume-title":"Conf. on Robot Learning (CoRL)","author":"Laskey","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487167"},{"key":"ref29","first-page":"144","volume-title":"A natural semantics for lazy evaluation","author":"Launchbury","year":"1993"},{"key":"ref30","author":"Mandlekar","year":"2020","journal-title":"Human-in-the-loop imitation learning using remote teleoperation"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968287"},{"key":"ref32","article-title":"Safe reinforcement learning using advantage-based intervention","volume-title":"International Conference on Machine Learning (ICML)","author":"Wagener","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref35","first-page":"2616","article-title":"Probabilistic movement primitives","volume-title":"Advances in neural information processing systems","author":"Paraschos","year":"2013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref37","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.005"},{"key":"ref39","article-title":"Where do you think you\u2019re going?: Inferring beliefs about dynamics from behavior","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Reddy","year":"2018"},{"key":"ref40","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Ross","year":"2011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref42","first-page":"1247","article-title":"Understanding teacher gaze patterns for robot learning","volume-title":"ser. Proceedings of Machine Learning Research","volume":"100","author":"Saran"},{"key":"ref43","article-title":"Trial without error: Towards safe rl with human intervention","volume-title":"17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Saunders","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341608"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.055"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196792"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00732"},{"key":"ref51","article-title":"Intervention aided reinforcement learning for safe and practical policy optimization in navigation","volume-title":"Conf. on Robot Learning (CoRL)","author":"Wang","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461203"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"ref54","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Association for the Advancement of Artificial Intelligence (AAAI)","author":"Ziebart","year":"2008"}],"event":{"name":"2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)","location":"Lyon, France","start":{"date-parts":[[2021,8,23]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9551387\/9551265\/09551469.pdf?arnumber=9551469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:32:01Z","timestamp":1706059921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9551469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/case49439.2021.9551469","relation":{},"subject":[],"published":{"date-parts":[[2021,8,23]]}}}