{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T22:53:12Z","timestamp":1774911192906,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,26]]},"DOI":"10.1109\/ro-man60168.2024.10731470","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T17:45:45Z","timestamp":1730310345000},"page":"303-310","source":"Crossref","is-referenced-by-count":4,"title":["EnQuery: Ensemble Policies for Diverse Query-Generation in Preference Alignment of Robot Navigation"],"prefix":"10.1109","author":[{"given":"Jorge","family":"de Heuvel","sequence":"first","affiliation":[{"name":"University of Bonn,Humanoid Robots Lab and the Center for Robotics,Germany"}]},{"given":"Florian","family":"Seiler","sequence":"additional","affiliation":[{"name":"University of Bonn,Humanoid Robots Lab and the Center for Robotics,Germany"}]},{"given":"Maren","family":"Bennewitz","sequence":"additional","affiliation":[{"name":"University of Bonn,Humanoid Robots Lab and the Center for Robotics,Germany"}]}],"member":"263","reference":[{"key":"ref1","author":"Christiano","year":"2017","journal-title":"Deep reinforcement learning from human preferences"},{"key":"ref2","author":"Kaufmann","year":"2023","journal-title":"A Survey of Reinforcement Learning from Human Feedback"},{"key":"ref3","author":"Ziegler","year":"2020","journal-title":"Fine-Tuning Language Models from Human Preferences"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.076"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341795"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610534"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610505"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2007.4415252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342081"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN53752.2022.9900554"},{"key":"ref13","article-title":"Asking Easy Questions: A User-Friendly Approach to Active Reward Learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"B\u0131y\u0131k"},{"key":"ref14","article-title":"Batch Active Preference-Based Learning of Reward Functions","volume-title":"Proceedings of The 2nd Conference on Robot Learning","author":"Biyik"},{"key":"ref15","author":"Wang","year":"2023","journal-title":"Aligning Large Language Models with Human: A Survey"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10562-9"},{"key":"ref17","article-title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Lee"},{"key":"ref18","article-title":"Maximizing ensemble diversity in deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Sheikh","year":"2021"},{"issue":"268","key":"ref19","article-title":"Stable-Baselines3: Reliable Reinforcement Learning Implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","article-title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","volume-title":"Proceedings of the 5th Conference on Robot Learning","author":"Li"},{"key":"ref21","author":"Coumans","year":"2016\/2021","journal-title":"Pybullet: Physics simulation for games visual effects robotics and reinforcement learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.107052"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06425-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"}],"event":{"name":"2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)","location":"Pasadena, CA, USA","start":{"date-parts":[[2024,8,26]]},"end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10731142\/10731137\/10731470.pdf?arnumber=10731470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T17:49:24Z","timestamp":1747676964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10731470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ro-man60168.2024.10731470","relation":{},"subject":[],"published":{"date-parts":[[2024,8,26]]}}}