{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:00:58Z","timestamp":1780635658771,"version":"3.54.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF"},{"name":"MLL Research Award"},{"name":"FLI"},{"name":"ARO"},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002186","name":"Lockheed Martin","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002186","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GM"},{"DOI":"10.13039\/100012884","name":"Robert Bosch (Australia) Pty","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012884","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/lra.2022.3146589","type":"journal-article","created":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T22:31:02Z","timestamp":1643322662000},"page":"4126-4133","source":"Crossref","is-referenced-by-count":48,"title":["Bottom-Up Skill Discovery From Unsegmented Demonstrations for Long-Horizon Robot Manipulation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2580-5748","authenticated-orcid":false,"given":"Yifeng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6795-420X","authenticated-orcid":false,"given":"Peter","family":"Stone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref2","article-title":"Temporal Abstraction in Reinforcement Learning","author":"Precup","year":"2000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980391"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913484072"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref6","first-page":"118","article-title":"The MAXQ method for hierarchical reinforcement learning","volume-title":"","volume":"98","author":"Dietterich","year":"1998"},{"key":"ref7","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vezhnevets","year":"2017"},{"key":"ref8","article-title":"Multi-level discovery of deep options","author":"Fox"},{"key":"ref9","article-title":"Variational intrinsic control","author":"Gregor"},{"key":"ref10","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","volume":"22","author":"Konidaris","year":"2009","journal-title":"Neural Inf. Process. Syst."},{"key":"ref11","article-title":"Option discovery using deep skill chaining","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bagaria","year":"2019"},{"key":"ref12","first-page":"744","article-title":"Expanding motor skills using relay networks","volume-title":"Proc. Conf. Robot Learn.","author":"Kumar","year":"2018"},{"key":"ref13","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018"},{"key":"ref14","article-title":"Learning an embedding space for transferable robot skills","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hausman","year":"2018"},{"key":"ref15","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sharma","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1996.506571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386006"},{"key":"ref18","first-page":"8624","article-title":"Learning robot skills with temporal variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shankar","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068891"},{"key":"ref20","article-title":"Compositional imitation learning: Explaining and executing one task at a time","author":"Kipf","year":"2018"},{"key":"ref21","first-page":"4654","article-title":"Learning task decomposition via temporal alignment for control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shiarlis","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref23","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proc. Int. Conf. Robot. Autom.","author":"Gupta","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561491"},{"key":"ref26","first-page":"1162","article-title":"Constructing skill trees for reinforcement learning agents from demonstration trajectories","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"23","author":"Konidaris","year":"2010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139383"},{"key":"ref28","article-title":"Modeling long-horizon tasks as sequential interaction landscapes","author":"Pirk","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461121"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793860"},{"issue":"1","key":"ref31","article-title":"The senses considered as perceptual systems","volume":"2","author":"Gibson","year":"1966","journal-title":"Houghton Mifflin Boston"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624198"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.517"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00914"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00094"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1986.1087032"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90053-M"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/544741.544798"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917743319"},{"key":"ref43","first-page":"2917","article-title":"Hierarchical imitation and reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Le","year":"2018"},{"key":"ref44","article-title":"Hindsight experience replay","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref45","article-title":"One-shot imitation learning","author":"Duan","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.024"},{"key":"ref47","article-title":"One-shot hierarchical imitation learning of compound visuomotor tasks","author":"Yu","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460689"},{"key":"ref49","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schaul","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.127.1.3"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref53","article-title":"Auto-Encoding Variational Bayes","author":"Kingma","year":"2013"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref55","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9647862\/9695333-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9647862\/09695333.pdf?arnumber=9695333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:20:51Z","timestamp":1705184451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9695333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":57,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3146589","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}