{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T17:33:07Z","timestamp":1779903187811,"version":"3.53.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["L233005"],"award-info":[{"award-number":["L233005"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125304"],"award-info":[{"award-number":["62125304"]}],"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":["62192751"],"award-info":[{"award-number":["62192751"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022YFA1004600"],"award-info":[{"award-number":["2022YFA1004600"]}]},{"name":"111 International Collaboration Project","award":["B25027"],"award-info":[{"award-number":["B25027"]}]},{"DOI":"10.13039\/501100001809","name":"Beijing National Research Center for Information Science and Technology (BNRist) Project","doi-asserted-by":"publisher","award":["BNR2024TD03003"],"award-info":[{"award-number":["BNR2024TD03003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3589271","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T17:44:57Z","timestamp":1752601497000},"page":"18737-18749","source":"Crossref","is-referenced-by-count":8,"title":["Preference-Based Multi-Objective Reinforcement Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7793-0953","authenticated-orcid":false,"given":"Ni","family":"Mu","sequence":"first","affiliation":[{"name":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1548-432X","authenticated-orcid":false,"given":"Yao","family":"Luan","sequence":"additional","affiliation":[{"name":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4683-7215","authenticated-orcid":false,"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Automation, Center for Intelligent and Networked Systems (CFINS), Beijing National Research Center for Information Science and Technology, and Beijing Key Laboratory of Embodied Intelligence Systems, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2698366"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119521"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8137-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2016.09.007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104352"},{"key":"ref6","article-title":"B-pref: Benchmarking preference-based reinforcement learning","volume-title":"arXiv:2111.03026","author":"Lee","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888918000292"},{"key":"ref9","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Lee"},{"key":"ref10","article-title":"Reinforcement learning and the reward engineering principle","volume-title":"Proc. AAAI Spring Symp. Ser.","author":"Dewey"},{"key":"ref11","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Christiano"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref14","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref15","first-page":"12154","article-title":"E-MAPP: Efficient multi-agent reinforcement learning with parallel program guidance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CAC59555.2023.10450595"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711622"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3559241"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CAC59555.2023.10450959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.122458"},{"key":"ref22","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref23","article-title":"Exploration by random network distillation","volume-title":"arXiv:1810.12894","author":"Burda","year":"2018"},{"key":"ref24","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rafailov"},{"key":"ref25","first-page":"8011","article-title":"Reward learning from human preferences and demonstrations in Atari","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ibarz"},{"key":"ref26","article-title":"S-EPOA: Overcoming the indistinguishability of segments with skill-driven preference-based reinforcement learning","author":"Mu","year":"2024","journal-title":"arXiv:2408.12130"},{"key":"ref27","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"arXiv:2203.10050","author":"Park","year":"2022"},{"key":"ref28","first-page":"2014","article-title":"Few-shot preference learning for human-in-the-loop RL","volume-title":"Proc. 6th Conf. Robot Learn. (CoRL)","volume":"205","author":"Hejna"},{"key":"ref29","first-page":"3008","article-title":"Learning to summarize with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Stiennon"},{"key":"ref30","first-page":"23671","article-title":"A toolkit for reliable benchmarking and research in multi-objective reinforcement learning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Felten"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-022-09552-y"},{"key":"ref32","article-title":"Human-in-the-loop policy optimization for preference-based multi-objective reinforcement learning","author":"Li","year":"2024","journal-title":"arXiv:2401.02160"},{"key":"ref33","first-page":"14636","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref34","article-title":"Multi-objective reinforcement learning for the expected utility of the return","volume-title":"Proc. Adapt. Learn. Agents Workshop FAIM","author":"Roijers"},{"key":"ref35","first-page":"10607","article-title":"Prediction-guided multi-objective reinforcement learning for continuous robot control","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Xu"},{"key":"ref36","first-page":"1110","article-title":"Pareto conditioned networks","volume-title":"Proc. 21st Int. Conf. Auto. Agents Multiagent Syst.","author":"Reymond"},{"key":"ref37","first-page":"2003","article-title":"Sample-efficient multi-objective learning via generalized policy improvement prioritization","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Alegre"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-5773-8","volume-title":"Linear Operator Theory in Engineering and Science","author":"Naylor","year":"1982"},{"key":"ref40","first-page":"1","article-title":"Convergence of q-learning: A simple proof","author":"Melo","year":"2001"},{"key":"ref41","article-title":"Decentralized multi-agent reinforcement learning: An off-policy method","author":"Li","year":"2021","journal-title":"arXiv:2111.00438"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3282257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CAC63892.2024.10865310"},{"key":"ref45","article-title":"Clarify: Contrastive preference reinforcement learning for untangling ambiguous queries","volume-title":"arXiv:2506.00388","author":"Mu","year":"2025"},{"key":"ref46","volume":"63","author":"Zitzler","year":"1999","journal-title":"Evolutionary Algorithms for Multiobjective Optimization: Methods and Applications"},{"key":"ref47","article-title":"Query-policy misalignment in preference-based reinforcement learning","volume-title":"arXiv:2305.17400","author":"Hu","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390162"},{"key":"ref50","volume-title":"An Environment for Autonomous Driving Decision-making","author":"Leurent","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.17083\/ijsg.v10i4.638"},{"key":"ref54","article-title":"Enhancing autonomous vehicle training with language model integration and critical scenario generation","author":"Tian","year":"2024","journal-title":"arXiv:2404.08570"},{"key":"ref55","article-title":"Listwise reward estimation for offline preference-based reinforcement learning","volume-title":"arXiv:2408.04190","author":"Choi","year":"2024"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11080487.pdf?arnumber=11080487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T18:32:54Z","timestamp":1753813974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11080487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3589271","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}