{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:25:07Z","timestamp":1774023907400,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343689","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"4579-4584","source":"Crossref","is-referenced-by-count":1,"title":["Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback"],"prefix":"10.1109","author":[{"given":"Suzie","family":"Kim","sequence":"first","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hye-Bin","family":"Shin","sequence":"additional","affiliation":[{"name":"Korea University,Department of Brain and Cognitive Engineering,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep reinforcement learning from human preferences","author":"Christiano","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref2","first-page":"2937","article-title":"Deep reinforcement learning in continuous action spaces: A case study in the game of simulated curling","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref3","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref4","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Park"},{"key":"ref5","article-title":"Reward uncertainty for exploration in preference-based reinforcement learning","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Liang"},{"key":"ref6","article-title":"RIME: Robust preference-based reinforcement learning with noisy preferences","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Cheng"},{"key":"ref7","article-title":"Breadcrumbs to the goal: Goal-conditioned exploration from human-in-the-loop feedback","author":"Villasevil","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-018-0501-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c"},{"key":"ref11","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196566"},{"key":"ref13","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-02891-8"},{"key":"ref15","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"MacGlashan"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161068"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636451"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i18.17998","article-title":"The EMPATHIC framework for task learning from implicit human feedback","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Cui"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460551"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341669"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09916-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/acabe9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3122969"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4059-14.2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1996.547658"},{"key":"ref28","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343689.pdf?arnumber=11343689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:37Z","timestamp":1770843037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343689","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}