{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:36:59Z","timestamp":1763203019443,"version":"3.44.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Shanghai Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["24511104000"],"award-info":[{"award-number":["24511104000"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R and D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161800"],"award-info":[{"award-number":["2022ZD0161800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127694","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1163-1169","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences"],"prefix":"10.1109","author":[{"given":"Ziang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjiao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Pharmacy, East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1961.287775"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211041652"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"issue":"136","key":"ref9","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"},{"article-title":"Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint","volume-title":"International Conference on Machine Learning","author":"Xiong","key":"ref10"},{"key":"ref11","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"NeurIPS"},{"key":"ref12","first-page":"21 406","article-title":"Avoiding side effects in complex environments","volume":"33","author":"Turner","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"A comprehensive survey of 1 lm alignment techniques: Rlhf, rlaif, ppo, dpo and more","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15348"},{"article-title":"B-pref: Benchmarking preference-based reinforcement learning","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Lee","key":"ref17"},{"key":"ref18","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv preprint"},{"article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"International Conference on Machine Learning","author":"Lee","key":"ref19"},{"key":"ref20","article-title":"Sequential preference ranking for efficient reinforcement learning from human feedback","volume":"36","author":"Hwang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Reward uncertainty for exploration in preference-based reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Liang","key":"ref21"},{"key":"ref22","article-title":"Exploiting unlabeled data for feedback efficient human preference based reinforcement learning","author":"Verma","year":"2023","journal-title":"arXiv preprint"},{"article-title":"SURF: Semi-supervised reward learning with data augmentation for feedbackefficient preference-based reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Park","key":"ref23"},{"key":"ref24","first-page":"2014","article-title":"Few-shot preference learning for human-in-the-loop rl","author":"Hejna","year":"2023","journal-title":"in CoRL. PMLR"},{"key":"ref25","first-page":"22270","article-title":"Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning","volume":"35","author":"Liu","year":"2022","journal-title":"in NeurIPS"},{"key":"ref26","article-title":"Unleashing the power of multitask learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341795"},{"article-title":"Flow to better: Offline preference-based reinforcement learning via preferred trajectory generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang","key":"ref28"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06295-5"},{"article-title":"Hindsight priors for reward learning from human preferences","volume-title":"International Conference on Learning Representations. OpenReview.net","author":"Verma","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28886"},{"article-title":"Preference transformer: Modeling human preferences using transformers for rl","volume-title":"Eleventh International Conference on Learning Representations. International Conference on Learning Representations","author":"Kim","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29666"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25825"},{"key":"ref37","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning. PMLR","author":"Sodhani"},{"key":"ref38","article-title":"Removing hidden confounding in recommendation: a unified multi-task learning approach","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3251897"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00785-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04905-6"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127694.pdf?arnumber=11127694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:05:37Z","timestamp":1756879537000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127694","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}