{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T02:37:05Z","timestamp":1770345425833,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"visiting professor by Ecole CentraleSupelec in Paris, France"},{"name":"Graduate Assistance in Areas of National Need (GAANN) Fellowship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/lra.2025.3583161","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T14:25:12Z","timestamp":1750861512000},"page":"8602-8609","source":"Crossref","is-referenced-by-count":1,"title":["Learning Human-Aware Robot Policies for Adaptive Assistance"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3180-4180","authenticated-orcid":false,"given":"Jason","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6330-6057","authenticated-orcid":false,"given":"Shikun","family":"Ban","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5483-0259","authenticated-orcid":false,"given":"Wentao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9888-6409","authenticated-orcid":false,"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1373-0294","authenticated-orcid":false,"given":"Dimitris","family":"Samaras","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197411"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iros47612.2022.9982244"},{"key":"ref3","first-page":"2105","article-title":"Learning representations that enable generalization in assistive tasks","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Zhi-Yang He","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611719"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981076"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-071223-105834"},{"key":"ref7","first-page":"62638","article-title":"Language models represent beliefs of self and others","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Zhu","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2229950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593525"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3308561.3353803"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2801475"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673309"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610705"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01868"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561430"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801640"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2016.7451736"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2812906"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6010"},{"key":"ref23","article-title":"Improving assistive robotics with deep reinforcement learning","volume-title":"Proc. NeurIPS\n2022 Deep Reinforcement Learn. Workshop","author":"Jakhotiya","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.04.009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981936"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142732"},{"key":"ref27","first-page":"42","article-title":"Aligning human and robot representations","volume-title":"Proc. 2024 ACM\/IEEE Int. Conf. Human-Robot Interaction","author":"Bobu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812442"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972852"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812302"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00931"},{"key":"ref34","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Lee","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3063927"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084198"},{"key":"ref37","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Park","year":"2022"},{"key":"ref38","first-page":"77675","article-title":"Social motion prediction with cognitive hierarchies","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Zhu","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref43","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref44","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11045364\/11050927.pdf?arnumber=11050927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T04:48:46Z","timestamp":1752727726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11050927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":44,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3583161","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}