{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:43:08Z","timestamp":1780674188974,"version":"3.54.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161336","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"909-916","source":"Crossref","is-referenced-by-count":15,"title":["Learning Video-Conditioned Policies for Unseen Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Elliot","family":"Chane-Sane","sequence":"first","affiliation":[{"name":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"Inria, École normale supérieure, CNRS, PSL Research University,Paris,France,75005"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1303","article-title":"Learning language-conditioned robot behavior from offline data and crowd-sourced annotation","author":"nair","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref12","article-title":"Language conditioned imitation learning over unstructured data","author":"lynch","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref14","article-title":"What matters in language conditioned robotic imitation learning","author":"mees","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref53","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref52","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Temporal difference models: Model-free deep rl for model-based control","author":"pong","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","author":"gupta","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref54","article-title":"Goal-conditioned imitation learning","volume":"32","author":"ding","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref18","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"khosla","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Training agents using upside-down reinforcement learning","author":"srivastava","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref50","article-title":"Reinforcement learning upside down: Don't predict rewards–just map them to actions","author":"schmidhuber","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref46","article-title":"Minedojo: Building open-ended embodied agents with internet-scale knowledge","author":"fan","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref45","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","author":"shridhar","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref48","article-title":"Generalized decision transformer for offline hindsight information matching","author":"furuta","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref47","article-title":"Rvs: What is essential for offline rl via supervised learning?","author":"emmons","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref42","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref41","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref49","article-title":"Reward-conditioned policies","author":"kumar","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"C-Iearning: Learning to achieve goals via recursive classification","author":"eysenbach","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"1113","article-title":"Learning latent plans from play","author":"lynch","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref9","article-title":"Visual reinforcement learning with imagined goals","volume":"31","author":"nair","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Actionable models: Unsupervised offline reinforcement learning of robotic skills","author":"chebotar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref3","first-page":"1078","article-title":"Aw-opt: Learning robotic skills with imitation andreinforcement at scale","author":"lu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref6","article-title":"Learning to reach goals via iterated supervised learning","author":"ghosh","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref5","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref35","article-title":"Masked visual pre-training for motor control","author":"xiao","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"R3m: A universal visual representation for robot manipulation","author":"nair","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref37","article-title":"Reinforcement learning with videos: Combining offline observations with interaction","author":"schmeckpeper","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref36","article-title":"Perceptual values from observation","author":"edwards","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Learning object manipulation skills via approximate state estimation from real videos","author":"petr\u00edk","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977835"},{"key":"ref2","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"jang","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref1","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"ahn","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref39","first-page":"19561","article-title":"Reinforcement learning with action-free pre-training from videos","author":"seo","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_42"},{"key":"ref24","article-title":"Model-based inverse reinforcement learning from visual demonstrations","author":"das","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref26","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275014"},{"key":"ref21","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref27","article-title":"Avid: Learning multi-stage tasks via pixel-level translation of human videos","author":"smith","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Online object representations with contrastive learning","author":"pirk","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161336.pdf?arnumber=10161336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:34:08Z","timestamp":1690220048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161336","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}