{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T22:09:29Z","timestamp":1776118169666,"version":"3.50.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2030859"],"award-info":[{"award-number":["2030859"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812402","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"8658-8665","source":"Crossref","is-referenced-by-count":17,"title":["Learning Periodic Tasks from Human Demonstrations"],"prefix":"10.1109","author":[{"given":"Jingyun","family":"Yang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Machine Learning Department"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Junwu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Mechanical Engineering"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Connor","family":"Settle","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Akshara","family":"Rai","sequence":"additional","affiliation":[{"name":"Meta AI."}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Rika","family":"Antonova","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Reinforcement learning with prototypical representations","author":"yarats","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref38","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume":"29","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"8583","article-title":"Planning to explore via self-supervised world models","author":"sekar","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref32","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Mastering atari with discrete world models","author":"hafner","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref30","first-page":"1113","article-title":"Learning latent plans from play","author":"lynch","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref37","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554676"},{"key":"ref35","first-page":"222","article-title":"A possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"0","journal-title":"Proc of the International Conference on Simulation of Adaptive Behavior From Animals to Animats"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00939"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.024"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2008.4760949"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.056"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587509"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.868681"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACVMOT.2005.91"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.18"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref51","article-title":"Keypoints into the future: Seff-supervised correspondence in model-based reinforcement learning","author":"manuelli","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3015448"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041514"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01040"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.620035"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1013335"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1139\/y04-070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543306"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926660"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651499"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref3","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","volume":"32","author":"sharma","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref5","author":"shao","year":"2020","journal-title":"Concept2robot Learning manipulation concepts from instructions and human demonstrations"},{"key":"ref8","article-title":"Few-shot bayesian imitation learning with logic over programs","volume":"abs 1904 6317","author":"silver","year":"2019","journal-title":"ArXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460689"},{"key":"ref49","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","author":"chebotar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Hierarchical foresight: Self-supervised learning of long-horizon tasks via visual subgoal generation","volume":"abs 1909 5829","author":"nair","year":"2020","journal-title":"ArXiv"},{"key":"ref46","article-title":"Mediapipe: A framework for building perception pipelines","author":"lugaresi","year":"2019","journal-title":"ar Xiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300016963"},{"key":"ref48","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref47","first-page":"5496","article-title":"Scalable global optimization via local Bayesian optimization","author":"eriksson","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","author":"srinivas","year":"2009","journal-title":"ArXiv Preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref43","article-title":"Unsupervised learning of object key-points for perception and control","volume":"32","author":"kulkarni","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812402.pdf?arnumber=9812402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:08Z","timestamp":1667516708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812402","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}