{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:28Z","timestamp":1766061628740,"version":"3.48.0"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246267","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"12561-12568","source":"Crossref","is-referenced-by-count":0,"title":["QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment"],"prefix":"10.1109","author":[{"given":"Yuyou","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yihang","family":"Yao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yaru","family":"Niu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Changyi","family":"Lin","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Yuxiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Wenhao","family":"Yu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Tingnan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jie","family":"Tan","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802439"},{"key":"ref3","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3400935"},{"key":"ref5","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"article-title":"Soloparkour: Constrained reinforcement learning for visual locomotion from privileged experience","volume-title":"8th Annual Conference on Robot Learning","author":"Chane-Sane","key":"ref8"},{"article-title":"SLR: Learning quadruped locomotion without privileged information","volume-title":"8th Annual Conference on Robot Learning","author":"Chen","key":"ref9"},{"article-title":"Learning h-infinity locomotion control","volume-title":"8th Annual Conference on Robot Learning","author":"Long","key":"ref10"},{"article-title":"Gaitor: Learning a unified representation across gaits for real-world quadruped locomotion","volume-title":"8th Annual Conference on Robot Learning","author":"Mitchell","key":"ref11"},{"article-title":"TOP-nav: Legged navigation integrating terrain, obstacle and proprioception estimation","volume-title":"8th Annual Conference on Robot Learning","author":"Ren","key":"ref12"},{"article-title":"Generalized animal imitator: Agile locomotion with versatile motion prior","volume-title":"8th Annual Conference on Robot Learning","author":"Yang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801980"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.059"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5040\/9781635577068-0320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127314"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128812"},{"key":"ref19","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Universal successor features for transfer reinforcement learning","year":"2020","author":"Ma","key":"ref20"},{"key":"ref21","first-page":"8025","article-title":"Policy caches with successor features","volume-title":"International Conference on Machine Learning","author":"Nemecek"},{"key":"ref22","first-page":"394","article-title":"Optimistic linear support and successor features as a basis for optimal policy transfer","volume-title":"International conference on machine learning","author":"Alegre"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-652-8_1"},{"issue":"1","key":"ref24","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of pareto dominating policies","volume":"15","author":"Van Moffaert","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3583743"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/10775463221124049"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128174"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01535"},{"key":"ref30","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International Conference on Machine Learning","author":"Achiam"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"issue":"1","key":"ref32","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"journal-title":"Constrained policy optimization via bayesian world models","year":"2022","author":"As","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25900"},{"key":"ref35","first-page":"13 644","article-title":"Constrained variational policy optimization for safe reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref36","first-page":"21 611","article-title":"Constrained decision transformer for offline safe reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref37","first-page":"25","article-title":"Gradient shaping for multi-constraint safe reinforcement learning","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Yao"},{"key":"ref38","first-page":"12 555","article-title":"Constraint-conditioned policy optimization for versatile safe reinforcement learning","volume":"36","author":"Yao","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33726"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ade2256"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104134"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610271"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160325"},{"journal-title":"Multi-agent manipulation via locomotion using hierarchical sim2real","year":"2019","author":"Nachum","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128478"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247166"},{"journal-title":"Robot parkour learning","year":"2023","author":"Zhuang","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610200"},{"key":"ref49","first-page":"773","article-title":"Fast and efficient locomotion via learned gait transitions","volume-title":"Conference on Robot Learning","author":"Yang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1121\/1.2773928"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"journal-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref52"},{"key":"ref53","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"International Conference on Machine Learning","author":"Stooke"},{"journal-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref54"},{"key":"ref55","first-page":"10 607","article-title":"Prediction-guided multi-objective reinforcement learning for continuous robot control","volume-title":"International conference on machine learning","author":"Xu"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246267.pdf?arnumber=11246267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:13Z","timestamp":1766061373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246267\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246267","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}