{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:15:05Z","timestamp":1789672505830,"version":"4.0.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L232021"],"award-info":[{"award-number":["L232021"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L242101"],"award-info":[{"award-number":["L242101"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473365"],"award-info":[{"award-number":["62473365"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2056"],"award-info":[{"award-number":["U22A2056"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373013"],"award-info":[{"award-number":["62373013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tsmc.2026.3663604","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:02:18Z","timestamp":1772830938000},"page":"4017-4029","source":"Crossref","is-referenced-by-count":1,"title":["LEASE: Offline Preference-Based Reinforcement Learning With High Sample Efficiency"],"prefix":"10.1109","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7407-2216","authenticated-orcid":false,"given":"Xiao-Yin","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9201-2700","authenticated-orcid":false,"given":"Guotao","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7602-4848","authenticated-orcid":false,"given":"Xiao-Hu","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-5840","authenticated-orcid":false,"given":"Zeng-Guang","family":"Hou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3078317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1980"},{"key":"ref5","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.26599\/tst.2025.9010120"},{"key":"ref7","first-page":"6765","article-title":"Inverse reward design","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hadfield-Menell"},{"key":"ref8","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref9","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref10","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3305498"},{"key":"ref12","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3388007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2025.3583392"},{"key":"ref15","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084198"},{"key":"ref17","article-title":"Reward uncertainty for exploration in preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref18","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref19","article-title":"Query-policy misalignment in preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref20","article-title":"Offline preference-based apprenticeship learning","author":"Shin","year":"2021","journal-title":"arXiv:2107.09251"},{"key":"ref21","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref22","article-title":"Flow to better: Offline preference-based reinforcement learning via preferred trajectory generation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref23","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref24","first-page":"4587","article-title":"MICRO: Model-based offline reinforcement learning with a conservative Bellman operator","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Liu"},{"key":"ref25","article-title":"Provable offline preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhan"},{"key":"ref26","first-page":"15753","article-title":"Beyond reward: Offline preference-guided policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref28","first-page":"124198","article-title":"SimPO: Simple preference optimization with a reference-free reward","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 37","author":"Chen"},{"key":"ref29","article-title":"Diverse preference optimization","author":"Lanchantin","year":"2025","journal-title":"arXiv:2501.18101"},{"key":"ref30","first-page":"12634","article-title":"Model alignment as prospect theoretic optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ethayarajh"},{"key":"ref31","first-page":"43037","article-title":"Principled reinforcement learning with human feedback from pairwise or K-wise comparisons","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref33","article-title":"DivideMix: Learning with noisy labels as semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref34","article-title":"In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rizve"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/494"},{"key":"ref36","volume":"135","author":"Sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref37","first-page":"1133","article-title":"A Bayesian approach for policy learning from trajectory preference queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Wilson"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref39","article-title":"Hindsight PRIORs for reward learning from human preferences","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Verma"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/jj.20206644.79"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2025.3578666"},{"key":"ref42","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref43","article-title":"What are the statistical limits of offline RL with linear function approximation?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref44","first-page":"5049","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref45","first-page":"25731","article-title":"Class-distribution-aware pseudo-labeling for semi-supervised multi-label learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xie"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_13"},{"key":"ref47","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref48","volume-title":"Empirical Processes in M-Estimation","volume":"6","author":"Geer","year":"2000"},{"key":"ref49","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref50","article-title":"Uni-RLHF: Universal platform and benchmark suite for reinforcement learning with diverse human feedback","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yuan"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11571037\/11424343.pdf?arnumber=11424343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:32:18Z","timestamp":1781929938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11424343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":50,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2026.3663604","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}