{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:39:45Z","timestamp":1791391185917,"version":"4.3.3"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004063","name":"Knut and Alice Wallenberg Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["BIRD-884807"],"award-info":[{"award-number":["BIRD-884807"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"H2020 CANOPIES","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981315","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"8660-8666","source":"Crossref","is-referenced-by-count":13,"title":["Back to the Manifold: Recovering from Out-of-Distribution States"],"prefix":"10.1109","author":[{"given":"Alfredo","family":"Reichlin","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giovanni Luca","family":"Marchetti","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Yin","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Ghadirzadeh","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref2","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref4","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross"},{"key":"ref5","article-title":"Plas: Latent action space for offline reinforcement learning","author":"Zhou","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Combo: Conservative offline model-based policy optimization","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759417"},{"key":"ref9","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"Kahn","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref11","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","author":"Ross"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179129"},{"key":"ref13","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"80","article-title":"Eligibility traces for off-policy policy evaluation","author":"Precup","year":"2000","journal-title":"Computer Science Department Faculty Publication Series"},{"key":"ref15","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2019"},{"key":"ref17","article-title":"Latent-variable advantage-weighted policy optimization for offline rl","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197125"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref22","article-title":"Learning to be safe: Deep rl with a safety critic","author":"Srinivasan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976272"},{"key":"ref24","first-page":"959","article-title":"Ls3: Latent space safe sets for long-horizon visuomotor control of sparse reward iterative tasks","volume-title":"Conference on Robot Learning","author":"Wilcox","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9643-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197505"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968596"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206046"},{"key":"ref32","article-title":"Data-efficient learning of feedback policies from image pixels using deep dynamical models","author":"Assael","year":"2015","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Learning to linearize under uncertainty","volume":"28","author":"Goroshin","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume":"28","author":"Watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"7444","article-title":"Solar: Deep structured representations for model-based reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Zhang","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00443"},{"key":"ref38","article-title":"Contrastive learning of structured world models","author":"Kipf","year":"2019","journal-title":"arXiv preprint"},{"key":"ref39","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"International conference on machine learning","author":"Cohen","year":"2016"},{"key":"ref40","article-title":"Equivariant representation learning via class-pose decomposition","author":"Marchetti","year":"2022","journal-title":"arXiv preprint"},{"key":"ref41","author":"Bishop","year":"1994","journal-title":"Mixture density networks"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3170427.3186500"},{"key":"ref43","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593513"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00731"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981315.pdf?arnumber=9981315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T08:36:15Z","timestamp":1709368575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981315","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}