{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:52:36Z","timestamp":1781848356180,"version":"3.54.5"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFB4708900"],"award-info":[{"award-number":["2024YFB4708900"]}]},{"name":"Zhongguancun Academy","award":["C20250301"],"award-info":[{"award-number":["C20250301"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/lra.2026.3699150","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:36:54Z","timestamp":1780342614000},"page":"9072-9079","source":"Crossref","is-referenced-by-count":0,"title":["Human-Guided Online Reward Adaptation for Real-Robot Arm Manipulation"],"prefix":"10.1109","volume":"11","author":[{"given":"Tianxing","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojia","family":"Ao","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-1957","authenticated-orcid":false,"given":"Guangyan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3265-3148","authenticated-orcid":false,"given":"Te","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6975-0158","authenticated-orcid":false,"given":"Chao","family":"Yu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6628-7946","authenticated-orcid":false,"given":"Yufeng","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ads5033"},{"key":"ref2","article-title":"$\\pi ^{*}_{0.6}$: A VLA that learns from experience","author":"Intelligence","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610040"},{"issue":"39","key":"ref4","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017"},{"key":"ref6","article-title":"VIP: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref7","first-page":"55681","article-title":"RoboCLIP: One demonstration is enough to learn robot policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sontakke","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_10"},{"key":"ref9","article-title":"$\\pi _{RL}$: Online RL fine-tuning for flow-based vision-language-action models","author":"Chen","year":"2025"},{"key":"ref10","article-title":"RLinf-VLA: A unified and efficient framework for VLA RL training","author":"Zang","year":"2025"},{"key":"ref11","article-title":"A framework for efficient robotic manipulation","volume-title":"Proc. Deep RL Workshop NeurIPS","author":"Zhan","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref14","first-page":"26516","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128466"},{"key":"ref16","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4409"},{"key":"ref18","article-title":"Pref-GUIDE: Continual policy learning from real-time human feedback via preference-based learning","author":"Ji","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247039"},{"key":"ref20","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"1999"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref23","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2011"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11570239\/11543318.pdf?arnumber=11543318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:23:11Z","timestamp":1781846591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11543318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":23,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3699150","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}