{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T04:15:04Z","timestamp":1773288904806,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Union's Horizon Europe Research and Innovation Programme","award":["101120732 (AUTOASSESS)"],"award-info":[{"award-number":["101120732 (AUTOASSESS)"]}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["864042 (AGILEFLIGHT)"],"award-info":[{"award-number":["864042 (AGILEFLIGHT)"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/lra.2024.3520894","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:34:22Z","timestamp":1734982462000},"page":"2112-2119","source":"Crossref","is-referenced-by-count":10,"title":["Multi-Task Reinforcement Learning for Quadrotors"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9939-6785","authenticated-orcid":false,"given":"Jiaxu","family":"Xing","sequence":"first","affiliation":[{"name":"Robotics and Perception Group, Department of Informatics, University of Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2940-0675","authenticated-orcid":false,"given":"Ismail","family":"Geles","sequence":"additional","affiliation":[{"name":"Robotics and Perception Group, Department of Informatics, University of Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6352-3744","authenticated-orcid":false,"given":"Yunlong","family":"Song","sequence":"additional","affiliation":[{"name":"Robotics and Perception Group, Department of Informatics, University of Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0590-0043","authenticated-orcid":false,"given":"Elie","family":"Aljalbout","sequence":"additional","affiliation":[{"name":"Robotics and Perception Group, Department of Informatics, University of Zurich, Zürich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3831-6778","authenticated-orcid":false,"given":"Davide","family":"Scaramuzza","sequence":"additional","affiliation":[{"name":"Robotics and Perception Group, Department of Informatics, University of Zurich, Zürich, Switzerland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adg1462"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610095"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811564"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4324\/9780203009864.ch12"},{"key":"ref7","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref8","article-title":"Scaling up multi-task robotic reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Kalashnikov","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref10","article-title":"Sharing knowledge in multi-task deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"D\u2019Eramo","year":"2020"},{"key":"ref11","article-title":"LIMT: Language-informed multi-task visual world models","author":"Aljalbout","year":"2024"},{"key":"ref12","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930489"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3421789"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611499"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref19","article-title":"Bootstrapping reinforcement learning with imitation for vision-based agile flight","volume-title":"Proc. Conf. Robot Learn.","author":"Xing","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.082"},{"key":"ref21","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yang","year":"2020"},{"key":"ref22","article-title":"Lifelong robotic reinforcement learning by retaining experiences","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Xie","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636053"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref25","article-title":"What matters in on-policy reinforcement learning? a large-scale empirical study","author":"Andrychowicz","year":"2020"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref27","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Proc. Conf. Robot Learn.","author":"Song","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abl6259"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10849592\/10812062.pdf?arnumber=10812062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T18:49:08Z","timestamp":1737658148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":28,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3520894","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}