{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:19Z","timestamp":1757608639745,"version":"3.44.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127396","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"7392-7398","source":"Crossref","is-referenced-by-count":0,"title":["Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Muhan","family":"Hou","sequence":"first","affiliation":[{"name":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"}]},{"given":"Koen","family":"Hindriks","sequence":"additional","affiliation":[{"name":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"}]},{"given":"A.E.","family":"Eiben","sequence":"additional","affiliation":[{"name":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"}]},{"given":"Kim","family":"Baraka","sequence":"additional","affiliation":[{"name":"Vrije Universiteit (VU) Amsterdam,Department of Computer Science,The Netherlands"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273565"},{"key":"ref2","first-page":"1621","article-title":"Efficient sim-to-real transfer of contact-rich manipulation skills with online admittance residual learning","volume-title":"in Conference on Robot Learning","author":"Zhang"},{"key":"ref3","article-title":"Adaptsim: Taskdriven simulation adaptation for sim-to-real transfer","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"article-title":"good robot! now watch this!: Repurposing reinforcement learning for task-to-task transfer","volume-title":"in 5th Annual Conference on Robot Learning","author":"Hundt","key":"ref4"},{"key":"ref5","first-page":"3789","article-title":"Policy stitching: Learning transferable robot policies","volume-title":"in Conference on Robot Learning","author":"Jian"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0142331216649655"},{"article-title":"Representing skill demonstrations for adaptation and transfer","volume-title":"in 2014 AAAI fall symposium series","author":"Fitzgerald","key":"ref7"},{"key":"ref8","first-page":"1896","article-title":"Acnmp: Skill transfer and task extrapolation through learning from demonstration and reinforcement learning via representation sharing","volume-title":"in Conference on Robot Learning","author":"Akbulut"},{"key":"ref9","article-title":"Cross-domain transfer via semantic skill imitation","author":"Pertsch","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"762","article-title":"Transferring hierarchical structures with dual meta imitation learning","volume-title":"in Conference on Robot Learning","author":"Gao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92307-5_77"},{"key":"ref12","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"in Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross"},{"key":"ref13","article-title":"Query-efficient imitation learning for end-toend autonomous driving","author":"Zhang","year":"2016","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05849-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970619"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3737892"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3687272.3688298"},{"key":"ref18","first-page":"5286","article-title":"Domain adaptive imitation learning","volume-title":"in International Conference on Machine Learning","author":"Kim"},{"key":"ref19","first-page":"3917","article-title":"An imitation from observation approach to transfer learning with dynamics mismatch","volume":"33","author":"Desai","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN57019.2023.10309481"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN57019.2023.10309326"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09459-6"},{"key":"ref23","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"ref26","first-page":"604","article-title":"The empathic framework for task learning from implicit human feedback","volume-title":"in Conference on Robot Learning","author":"Cui"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33950-0_31"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08118-z"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0839-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref32","article-title":"Awac: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"in International conference on machine learning","author":"Haarnoja"},{"key":"ref34","article-title":"panda-gym: Open-Source Goal-Conditioned Environments for Robotic Learning","author":"Gallou\u00e9dec","year":"2021","journal-title":"4th Robot Learning Workshop: Self-Supervised and Lifelong Learning at NeurIPS"},{"key":"ref35","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume-title":"in International Conference on Machine Learning","author":"Ball"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"101532","DOI":"10.1016\/j.softx.2023.101532","article-title":"Taming the panda with python: A powerful duo for seamless robotics programming and integration","volume":"24","author":"Elsner","year":"2023","journal-title":"SoftwareX"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127396.pdf?arnumber=11127396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:04:39Z","timestamp":1756879479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127396","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}