{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:51:10Z","timestamp":1761061870818,"version":"3.37.3"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T00:00:00Z","timestamp":1693008000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,26]],"date-time":"2023-08-26T00:00:00Z","timestamp":1693008000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,26]]},"DOI":"10.1109\/case56687.2023.10260484","type":"proceedings-article","created":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T17:32:23Z","timestamp":1695922343000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Learn from Robot: Transferring Skills for Diverse Manipulation via Cycle Generative Networks"],"prefix":"10.1109","author":[{"given":"Quantao","family":"Yang","sequence":"first","affiliation":[{"name":"Center for Applied Autonomous Sensor Systems (AASS), Örebro University,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes A.","family":"Stork","sequence":"additional","affiliation":[{"name":"Center for Applied Autonomous Sensor Systems (AASS), Örebro University,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todor","family":"Stoyanov","sequence":"additional","affiliation":[{"name":"Center for Applied Autonomous Sensor Systems (AASS), Örebro University,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811668"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184805"},{"key":"ref14","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01117"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref16","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"mandlekar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref24","first-page":"2725","article-title":"Meta reinforcement learning for sim-to-real domain adaptation","author":"arndt","year":"0","journal-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref23","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref26","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","author":"pertsch","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref20","first-page":"247","article-title":"Task-relevant adversarial imitation learning","author":"zolna","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref22","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196582"},{"key":"ref28","first-page":"1278","article-title":"Stochastic backprop-agation and approximate inference in deep generative models","author":"rezende","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref27","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"CoRR vol abs\/1312 6114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3187276"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636628"},{"key":"ref7","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref9","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref4","article-title":"Hardware conditioned policies for multi-robot transfer learning","volume":"31","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2900768"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"}],"event":{"name":"2023 IEEE 19th International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2023,8,26]]},"location":"Auckland, New Zealand","end":{"date-parts":[[2023,8,30]]}},"container-title":["2023 IEEE 19th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10260321\/10260291\/10260484.pdf?arnumber=10260484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T17:54:49Z","timestamp":1697478889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10260484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,26]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/case56687.2023.10260484","relation":{},"subject":[],"published":{"date-parts":[[2023,8,26]]}}}