{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:19:21Z","timestamp":1773141561799,"version":"3.50.1"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610505","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"2288-2295","source":"Crossref","is-referenced-by-count":9,"title":["POLITE: Preferences Combined with Highlights in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Simon","family":"Holk","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"}]},{"given":"Daniel","family":"Marta","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"}]},{"given":"Iolanda","family":"Leite","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Robotics, Perception and Learning, School of Electrical Engineering and Computer Science,Stockholm,Sweden,114 28"}]}],"member":"263","reference":[{"issue":"136","key":"ref1","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Int. Conf. on Machine Learning","author":"Ng"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889398"},{"key":"ref5","first-page":"7413","article-title":"Preference learning along multiple criteria: A game-theoretic perspective","volume-title":"Advances in neural information processing systems","volume":"33","author":"Bhatia"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1754.001.0001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-016-0038-6"},{"key":"ref8","article-title":"Causal confusion in imitation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"De Haan"},{"key":"ref9","article-title":"A study of causal confusion in preference-based reward learning","author":"Tien","year":"2022"},{"key":"ref10","article-title":"Human-ai shared control via policy dissection","author":"Li","year":"2022"},{"key":"ref11","first-page":"181","article-title":"Second thoughts are best: Learning to re-align with human values from text edits","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Liu"},{"key":"ref12","article-title":"Interaction-grounded learning with action-inclusive feedback","author":"Xie","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.584075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.065"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460854"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02675-6_46"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.03.015"},{"key":"ref19","first-page":"160","article-title":"Deep reinforcement learning of abstract reasoning from demonstrations","volume-title":"2018 13th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","author":"Clark-Turner"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673256"},{"key":"ref21","article-title":"The empathic framework for task learning from implicit human feedback","author":"Cui","year":"2020"},{"key":"ref22","first-page":"216","article-title":"Feature expansive reward learning: Rethinking human input","volume-title":"Proceedings of the 2021 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Bobu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584055"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064500"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.048"},{"key":"ref27","article-title":"Maximum likelihood constraint inference for inverse reinforcement learning","author":"Scobee","year":"2019"},{"key":"ref28","first-page":"649","article-title":"Teaching a robot tasks of arbitrary complexity via human feedback","volume-title":"Proceedings of the 2020 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Wang"},{"key":"ref29","first-page":"659","article-title":"Joint goal and strategy inference across heterogeneous demonstrators via reward network distillation","volume-title":"Proceedings of the 2020 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Chen"},{"key":"ref30","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"International conference on machine learning","author":"Brown"},{"key":"ref31","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Conference on robot learning","author":"Brown"},{"key":"ref32","first-page":"629","article-title":"Interactive tuning of robot program parameters via expected divergence maximization","volume-title":"Proceedings of the 2020 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Racca"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.055"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889616"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.028"},{"key":"ref39","article-title":"Models of human preference for learning reward functions","author":"Knox","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161261"},{"key":"ref41","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Jeon"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634970"},{"key":"ref43","first-page":"429","article-title":"Less is more: Rethinking probabilistic models of human behavior","volume-title":"Proceedings of the 2020 acm\/ieee international conference on human-robot interaction","author":"Bobu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341795"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.041"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"ref48","article-title":"Repeated inverse reinforcement learning","volume-title":"Advances in neural information processing systems","volume":"30","author":"Amin"},{"key":"ref49","article-title":"Deep reinforcement learning from human preferences","volume-title":"Advances in neural information processing systems","volume":"30","author":"Christiano"},{"key":"ref50","article-title":"Performance evaluation of imitation learning algorithms with human experts","author":"B\u00e5venstrand","year":"2019"},{"key":"ref51","article-title":"Reward learning from human preferences and demonstrations in atari","volume-title":"Advances in neural information processing systems","volume":"31","author":"Ibarz"},{"key":"ref52","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021"},{"key":"ref53","article-title":"Few-shot preference learning for human-in-the-loop rl","author":"Hejna","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800101"},{"key":"ref55","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2016"},{"key":"ref56","article-title":"Learning to navigate in complex environments","author":"Mirowski","year":"2016"},{"key":"ref57","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","volume-title":"Conference on Robot Learning","author":"Matas"},{"key":"ref58","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"Shelhamer","year":"2016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"ref60","first-page":"167","article-title":"Using natural language and program abstractions to instill human inductive biases in machines","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Kumar"},{"key":"ref61","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref62","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3128237"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610505.pdf?arnumber=10610505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:50:19Z","timestamp":1723269019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610505","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}