{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:01:06Z","timestamp":1768003266562,"version":"3.49.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Wallenberg AI"},{"name":"Autonomous Systems and Software Program"},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/lra.2022.3184805","type":"journal-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T19:36:18Z","timestamp":1655926578000},"page":"7652-7659","source":"Crossref","is-referenced-by-count":9,"title":["MPR-RL: Multi-Prior Regularized Reinforcement Learning for Knowledge Transfer"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5655-0990","authenticated-orcid":false,"given":"Quantao","family":"Yang","sequence":"first","affiliation":[{"name":"Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3958-6179","authenticated-orcid":false,"given":"Johannes A.","family":"Stork","sequence":"additional","affiliation":[{"name":"Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6013-4874","authenticated-orcid":false,"given":"Todor","family":"Stoyanov","sequence":"additional","affiliation":[{"name":"Autonomous Mobile Manipulation lab at the Center for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2900768"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562091"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.06.007"},{"key":"ref6","article-title":"Learning impedance actions for safe reinforcement learning in contact-rich tasks","volume-title":"Proc. NeurIPS Workshop Deployable Decis. Mak. Embodied Syst.","author":"Yang","year":"2021"},{"key":"ref7","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","volume-title":"Proc. Conf. Robot Learn.","author":"Pertsch","year":"2020"},{"key":"ref8","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","volume-title":"Proc. Conf. Robot Learn.","author":"James","year":"2017"},{"issue":"7","key":"ref9","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","first-page":"281","article-title":"Mutual alignment transfer learning","volume-title":"Proc. Conf. Robot Learn.","author":"Wulfmeier","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793556"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref13","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"Gupta","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593933"},{"key":"ref16","first-page":"1162","article-title":"Active domain randomization","volume-title":"Proc. Conf. Robot Learn.","author":"Mehta","year":"2020"},{"key":"ref17","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","volume-title":"Proc. Conf. Robot Learn.","author":"Muratore","year":"2018"},{"key":"ref18","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref19","article-title":"How to train your MAML","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Antoniou","year":"2019"},{"key":"ref20","article-title":"ES-MAML: Simple hessian-free meta learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref21","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clavera","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340848"},{"key":"ref24","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref25","article-title":"Demonstration-guided reinforcement learning with learned skills","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Pertsch","year":"2021"},{"key":"ref26","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singh","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146589"},{"key":"ref28","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2014"},{"key":"ref29","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Int. Conf. Mach. Learn.","author":"Rezende","year":"2014"},{"key":"ref30","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref31","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09803274.pdf?arnumber=9803274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:32:35Z","timestamp":1706761955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9803274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":31,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3184805","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}