{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:17:35Z","timestamp":1773141455619,"version":"3.50.1"},"reference-count":41,"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\/icra57147.2024.10611472","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"2814-2821","source":"Crossref","is-referenced-by-count":6,"title":["A Generalized Acquisition Function for Preference-based Reward Learning"],"prefix":"10.1109","author":[{"given":"Evan","family":"Ellis","sequence":"first","affiliation":[{"name":"UC Berkeley,Department of Electrical Engineering and Computer Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav R.","family":"Ghosal","sequence":"additional","affiliation":[{"name":"UC Berkeley,Department of Electrical Engineering and Computer Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stuart J.","family":"Russell","sequence":"additional","affiliation":[{"name":"UC Berkeley,Department of Electrical Engineering and Computer Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anca","family":"Dragan","sequence":"additional","affiliation":[{"name":"UC Berkeley,Department of Electrical Engineering and Computer Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erdem","family":"B\u0131y\u0131k","sequence":"additional","affiliation":[{"name":"UC Berkeley,Department of Electrical Engineering and Computer Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9460","article-title":"Defining and characterizing reward gaming","volume":"35","author":"Skalse","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.053"},{"key":"ref3","article-title":"Asking easy questions: A user-friendly approach to active reward learning","volume-title":"Proceedings of the 3rd Conference on Robot Learning (CoRL)","author":"Biyik"},{"key":"ref4","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","volume":"99","author":"Ng"},{"key":"ref5","author":"Skalse","year":"2023","journal-title":"Invariance in policy optimisation and partial identifiability in reward learning"},{"key":"ref6","article-title":"A general framework for reward function distances","volume-title":"NeurIPS ML Safety Workshop","author":"Jenner"},{"key":"ref7","article-title":"Quantifying differences in reward functions","volume-title":"International Conference on Learning Representations","author":"Gleave"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Learning multimodal rewards from rankings","volume-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)","author":"Myers"},{"key":"ref11","first-page":"217","article-title":"Learning robot objectives from physical human interaction","volume-title":"Conference on Robot Learning","author":"Bajcsy"},{"key":"ref12","first-page":"141","article-title":"Learning from physical human corrections, one feature at a time","volume-title":"Proceedings of the 2018 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Bajcsy"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/32"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.4.590"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341530"},{"key":"ref16","author":"Lindner","year":"2022","journal-title":"Information directed reward learning for reinforcement learning"},{"key":"ref17","author":"Wang","year":"2024","journal-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback"},{"key":"ref18","author":"Wulfe","year":"2022","journal-title":"Dynamics-aware comparison of learned reward functions"},{"key":"ref19","author":"Balakrishnan","year":"2020","journal-title":"Efficient exploration of reward functions in inverse reinforcement learning via bayesian optimization"},{"key":"ref20","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume":"33","author":"Jeon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","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":"ref22","first-page":"1","article-title":"Gaussian processes for ordinal regression","volume":"6","author":"Chu","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560840"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.041"},{"key":"ref26","first-page":"02 783 649","article-title":"Active preference-based gaussian process regression for reward learning and optimization","author":"B\u0131y\u0131k","year":"2023","journal-title":"The International Journal of Robotics Research"},{"key":"ref27","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Icml","volume":"1","author":"Ng"},{"key":"ref28","article-title":"Learning reward functions from scale feedback","volume-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)","author":"Wilde"},{"key":"ref29","first-page":"427","article-title":"Adaptive submodularity: Theory and applications in active learning and stochastic optimization","volume":"42","author":"Golovin","year":"2011","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref30","article-title":"Near-optimal bayesian active learning with noisy observations","volume":"23","author":"Golovin","year":"2010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Modified group generalized binary search with near-optimal performance guarantees","author":"Gowtham Bellala","year":"2010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icra40945.2020.9197411"},{"key":"ref33","first-page":"5988","article-title":"Understanding dataset difficulty with V-usable information","volume-title":"International Conference on Machine Learning","author":"Ethayarajh"},{"key":"ref34","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.148"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/1225957"},{"key":"ref38","first-page":"37","article-title":"A formula for predicting readability: Instructions","author":"Dale","year":"1948","journal-title":"Educational research bulletin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1037\/h0076540"},{"key":"ref40","article-title":"Automated readability index","author":"Senter","year":"1967","journal-title":"Technical report, DTIC document, Tech. Rep."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449863"}],"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\/10611472.pdf?arnumber=10611472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:12:18Z","timestamp":1723349538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611472","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}