{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:14:03Z","timestamp":1774368843869,"version":"3.50.1"},"reference-count":29,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403366"],"award-info":[{"award-number":["62403366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["22120240291"],"award-info":[{"award-number":["22120240291"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013105","name":"Shanghai Rising-Star Program","doi-asserted-by":"publisher","award":["23YF1449700"],"award-info":[{"award-number":["23YF1449700"]}],"id":[{"id":"10.13039\/501100013105","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/lra.2025.3583508","type":"journal-article","created":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:45:09Z","timestamp":1750959909000},"page":"8155-8162","source":"Crossref","is-referenced-by-count":5,"title":["NeuTRL: Neural Trust-Guided Reinforcement Learning for Human-Robot Collaboration"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2070-1475","authenticated-orcid":false,"given":"Caiyue","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8026-1328","authenticated-orcid":false,"given":"Hongrui","family":"Sang","sequence":"additional","affiliation":[{"name":"School of Logistics Engineering, Shanghai Maritime University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3285-0072","authenticated-orcid":false,"given":"Changming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7824-1179","authenticated-orcid":false,"given":"Yanmin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4632-9170","authenticated-orcid":false,"given":"Zhipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6003-7719","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21236\/ad0289565"},{"key":"ref3","first-page":"5174","article-title":"On the utility of learning about humans for human-AI coordination","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Carroll","year":"2019"},{"key":"ref4","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang","year":"2022"},{"key":"ref5","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Christiano","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.03.009"},{"key":"ref7","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"MacGlashan","year":"2017"},{"key":"ref8","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2584"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145516"},{"key":"ref12","article-title":"Open problems and fundamental limitations of reinforcement learning from human feedback","author":"Casper","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref13","first-page":"604","article-title":"The empathic framework for task learning from implicit human feedback","volume-title":"Proc. Conf. Robot Learn.","author":"Cui","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3046353"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3132743"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3137015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2886406"},{"key":"ref19","article-title":"A theoretical framework for partially-observed reward-states in RLHF","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Kausik","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3717.001.0001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610156"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0018720811417254"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3438040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3359616"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.01.028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919866905"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref28","article-title":"Population based training of neural networks","author":"Jaderberg","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11045364\/11051237.pdf?arnumber=11051237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T17:52:22Z","timestamp":1751651542000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11051237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":29,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3583508","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}