{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:40:09Z","timestamp":1791391209490,"version":"4.3.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"IIIS"},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Todor Stoyanov"},{"name":"Wallenberg AI, Autonomous Systems, and Software Program"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EFRI-2318065"],"award-info":[{"award-number":["EFRI-2318065"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["FRR-2145283"],"award-info":[{"award-number":["FRR-2145283"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-22-1-2204"],"award-info":[{"award-number":["N00014-22-1-2204"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UT Good Systems"},{"name":"Machine Learning Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/lra.2024.3443610","type":"journal-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:47:25Z","timestamp":1723744045000},"page":"8322-8329","source":"Crossref","is-referenced-by-count":13,"title":["PRIME: Scaffolding Manipulation Tasks With Behavior Primitives for Data-Efficient Imitation Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6980-0047","authenticated-orcid":false,"given":"Tian","family":"Gao","sequence":"first","affiliation":[{"name":"Department of Computer Science, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soroush","family":"Nasiriany","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5931-0287","authenticated-orcid":false,"given":"Huihan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5655-0990","authenticated-orcid":false,"given":"Quantao","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref2","first-page":"1199","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Proc. Conf. Robot Learn.","author":"Zhu","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref4","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref6","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Mandlekar","year":"2021"},{"key":"ref7","volume-title":"Temporal Abstraction in Reinforcement Learning","author":"Precup","year":"2000"},{"key":"ref8","article-title":"Learning and retrieval from prior data for skill-based imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Nasiriany","year":"2022"},{"key":"ref9","article-title":"Opal: Offline primitive discovery for accelerating offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ajay","year":"2021"},{"key":"ref10","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Proc. Conf. Robot Learn.","author":"Pertsch","year":"2021"},{"key":"ref11","article-title":"Discovering motor programs by recomposing demonstrations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shankar","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146589"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref14","first-page":"21847","article-title":"Accelerating robotic reinforcement learning via parameterized action primitives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dalal","year":"2021"},{"key":"ref15","first-page":"358","article-title":"Predicting object interactions with behavior primitives: An application in stowing tasks","volume-title":"Proc. Conf. Robot Learn.","author":"Chen","year":"2023"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1109\/TRO.2024.3353075","article-title":"Multi-stage cable routing through hierarchical imitation learning","volume":"40","author":"Luo","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2014.00062"},{"key":"ref19","first-page":"1930","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Toussaint","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2289018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196958"},{"key":"ref25","first-page":"4654","article-title":"TACO: Learning task decomposition via temporal alignment for control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shiarlis","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref27","article-title":"Weakly-supervised trajectory segmentation for learning reusable skills","volume-title":"Proc. ICLR 2020 Workshop Bridging AI Cogn. Sci.","author":"Mahmoudieh","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref29","article-title":"Planning from pixels using inverse dynamics models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Paster","year":"2021"},{"key":"ref30","first-page":"42339","article-title":"Semi-supervised offline reinforcement learning with action-free trajectories","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng","year":"2023"},{"key":"ref31","article-title":"Inverse dynamics pretraining learns good representations for multitask imitation","author":"Brandfonbrener","year":"2023","journal-title":"37th Proc. Conf. Neural Inf. Process. Syst."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010750"},{"key":"ref33","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Du","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329407"},{"key":"ref36","article-title":"Probabilistic movement primitives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Paraschos","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9364328"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref39","article-title":"Learning to generalize across long-horizon tasks from human demonstrations","author":"Mandlekar","year":"2020","journal-title":"Robot.: Sci. Syst."},{"key":"ref40","article-title":"Demonstration-guided reinforcement learning with learned skills","volume-title":"Proc. Conf. Robot Learn.","author":"Pertsch","year":"2021"},{"key":"ref41","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singh","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"key":"ref44","first-page":"25611","article-title":"How to leverage unlabeled data in offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2022"},{"key":"ref45","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Proc. Conf. Robot Learn.","author":"Lynch","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref49","article-title":"Discovering motor programs by recomposing demonstrations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shankar","year":"2019"},{"key":"ref50","first-page":"8624","article-title":"Learning robot skills with temporal variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shankar","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref52","first-page":"418","article-title":"DDCO: Discovery of deep continuous options for robot learning from demonstrations","volume-title":"Proc. Conf. robot Learn.","author":"Krishnan","year":"2017"},{"key":"ref53","article-title":"Deep reinforcement learning in parameterized action space","volume":"abs\/1511.04143","author":"Hausknecht","year":"2015","journal-title":"CoRR"},{"key":"ref54","article-title":"Learning to coordinate manipulation skills via skill behavior diversification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196619"},{"key":"ref56","article-title":"Waypoint-based imitation learning for robotic manipulation","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Shi","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref58","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref59","first-page":"306","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","volume-title":"Proc. Conf. Robot Learn.","author":"Tremblay","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10638067\/10637675-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10638067\/10637675.pdf?arnumber=10637675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:07:37Z","timestamp":1725250057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10637675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3443610","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}