{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:03:09Z","timestamp":1777636989112,"version":"3.51.4"},"reference-count":78,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128756","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"7377-7384","source":"Crossref","is-referenced-by-count":4,"title":["Personalization in Human-Robot Interaction Through Preference-Based Action Representation Learning"],"prefix":"10.1109","author":[{"given":"Ruiqi","family":"Wang","sequence":"first","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dayoon","family":"Suh","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohua","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Beijing University of Chemical Technology (BUCT),Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung-Cheol","family":"Min","sequence":"additional","affiliation":[{"name":"Purdue University,SMART Laboratory,Department of Computer and Information Technology,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00811-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341410"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366414"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102432"},{"key":"ref5","first-page":"319","article-title":"Personalization in hri: A longitudinal field experiment","volume-title":"Proceedings of the seventh annual ACMIIEEE international conference on Human-Robot Interaction","author":"Lee","year":"2012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673076"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10040120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917690593"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181676"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9764-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803320"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3511047.3537686"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518732"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-020-00629-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_8"},{"key":"ref18","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981616"},{"key":"ref20","first-page":"6152","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and un-supervised pre-training","volume-title":"International Conference on Machine Learning","author":"Lee","year":"2021"},{"key":"ref21","first-page":"18560","article-title":"Discor: Corrective feedback in reinforcement learning via distribution correction","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"B-pref: Benchmarking preference-based reinforcement learning","author":"Lee","year":"2021","journal-title":"Neural Information Processing Systems (Neu rIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10006-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-51532-8_10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3316782.3316791"},{"key":"ref26","first-page":"649","article-title":"Teaching a robot tasks of arbitrary complexity via human feedback","volume-title":"Proceedings of the 2020 ACMIIEEE International Conference on Human-Robot Interaction","author":"Wang","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3186270"},{"key":"ref28","first-page":"738","article-title":"A dual representation framework for robot learning with human guidance","volume-title":"Conference on Robot Learning","author":"Zhang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981076"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3528663"},{"key":"ref31","first-page":"2014","article-title":"Few-shot preference learning for human-in-the-loop rl","volume-title":"Conference on Robot Learning","author":"Hejna","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2843122"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262450"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3178807"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3029798.3038381"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.06.017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-020-01183-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN53752.2022.9900554"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.061"},{"key":"ref40","article-title":"Dexmv: Imitation learning for dexterous manipulation from human videos","volume-title":"International Conference on Learning Representations","author":"Qin","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2009.5326042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11060126"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2540623"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3582688"},{"key":"ref47","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"Julian","year":"2020","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197159"},{"key":"ref50","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref52","first-page":"27652","article-title":"Non-markovian reward modelling from trajectory labels via interpretable multiple in-stance learning","volume":"35","author":"Early","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","article-title":"Preference transformer: Modeling human preferences using transformers for rl","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kim","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29666"},{"key":"ref55","article-title":"Guide your agent with adaptive multi-modal rewards","volume":"36","author":"Kim","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref56","article-title":"Prefmmt: Modeling human preferences in preference-based reinforcement learning with multi-modal transformers","author":"Zhao","year":"2024","journal-title":"ar Xiv preprint arXiv"},{"key":"ref57","first-page":"27730","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":"ref58","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref60","first-page":"941","article-title":"Learning action representations for reinforcement learning","volume-title":"International conference on machine learning","author":"Chandak","year":"2019"},{"key":"ref61","article-title":"For sale: State-action representation learning for deep reinforcement learning","volume":"36","author":"Fujimoto","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","article-title":"Taco: Temporal latent action-driven contrastive loss for visual reinforcement learning","volume":"36","author":"Zheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref63","first-page":"1431","article-title":"Plannable approximations to mdp homomorphisms: Equivariance under actions","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"van der Pol","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197197"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561232"},{"key":"ref66","article-title":"Self-supervised policy adaptation during de-ployment","volume-title":"International Conference on Learning Representations","author":"Hansen","year":"2021"},{"key":"ref67","first-page":"683","article-title":"Robot learning with sensorimotor pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","year":"2023"},{"key":"ref68","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610421"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342201"},{"key":"ref71","first-page":"37","article-title":"Autoencoders, unsupervised learning, and deep architectures","volume-title":"Proceedings of ICML workshop on unsupervised and transfer learning. JMLR Workshop and Conference Proceedings","author":"Baldi","year":"2012"},{"key":"ref72","article-title":"Contrastive learning of structured world models","author":"Kipf","year":"2019","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref74","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume":"3","author":"Higgins","year":"2017","journal-title":"ICLR (Poster)"},{"key":"ref75","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref76","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref77","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"ar Xiv preprint arXiv"},{"key":"ref78","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11128756.pdf?arnumber=11128756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:08:45Z","timestamp":1756879725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128756","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}