{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:54:08Z","timestamp":1770281648558,"version":"3.49.0"},"reference-count":31,"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\/icra48891.2023.10160421","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"2944-2950","source":"Crossref","is-referenced-by-count":19,"title":["Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions"],"prefix":"10.1109","author":[{"given":"Chenhao","family":"Li","sequence":"first","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Blaes","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Kolev","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marin","family":"Vlastelica","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Frey","sequence":"additional","affiliation":[{"name":"ETH Zurich,Robotic Systems Lab,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Martius","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Learning more skills through optimistic exploration","author":"strouse","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref12","article-title":"Dynamics-aware unsupervised discovery of skills","author":"sharma","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref31","first-page":"25746","article-title":"Reward is enough for convex mdps","author":"zahavy","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"makoviychuk","year":"2021","journal-title":"Neural Information Processing Systems Datasets and Benchmarks Track"},{"key":"ref11","article-title":"Fast task inference with variational intrinsic successor features","author":"hansen","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref10","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref17","article-title":"Advanced skills through multiple adversarial motion priors in reinforcement learning","author":"vollenweider","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"1","article-title":"Apprenticeship learning via inverse rein-forcement learning","author":"abbeel","year":"0","journal-title":"Proceedings of the twenty-first international conference on Machine learning"},{"key":"ref19","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref18","article-title":"Variational information max-imisation for intrinsically motivated reinforcement learning","volume":"28","author":"mohamed","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"8198","article-title":"One solution is not all you need: Few-shot extrapolation via structured maxent RL","volume":"33","author":"kumar","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Information maximization in noisy channels: A variational approach","volume":"16","author":"barber","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref20","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref22","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","author":"campos","year":"0","journal-title":"Int Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16832"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2976639"},{"key":"ref27","article-title":"Variational option discovery algorithms","author":"achiam","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Learning agile skills via adversarial imitation of rough partial demonstrations","author":"li","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref9","article-title":"Variational intrinsic control","author":"gregor","year":"0","journal-title":"International Conference on Learning Representations Workshop Track Proceedings"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref5","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"}],"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\/10160421.pdf?arnumber=10160421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:32:46Z","timestamp":1690219966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160421","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}