{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:28:12Z","timestamp":1777994892800,"version":"3.51.4"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4702900"],"award-info":[{"award-number":["2022YFB4702900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFE0110200"],"award-info":[{"award-number":["2023YFE0110200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62027813"],"award-info":[{"award-number":["62027813"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Science Fund for Distinguished Young Scholars","award":["JQ21016"],"award-info":[{"award-number":["JQ21016"]}]},{"name":"Beijing Haidian Joint Fund","award":["L232038"],"award-info":[{"award-number":["L232038"]}]},{"DOI":"10.13039\/501100012492","name":"Excellent Member of Chinese Academy of Sciences (CAS) Youth Innovation Promotion Association","doi-asserted-by":"publisher","award":["Y2022054"],"award-info":[{"award-number":["Y2022054"]}],"id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3452944","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T14:32:51Z","timestamp":1726237971000},"page":"12680-12694","source":"Crossref","is-referenced-by-count":2,"title":["Few-Human-Interaction Reinforcement Learning for Autonomous Transbronchial Intervention"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4708-2245","authenticated-orcid":false,"given":"Gui-Bin","family":"Bian","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7918-2750","authenticated-orcid":false,"given":"Xiang-Rong","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Information Science and Technology University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4950-9812","authenticated-orcid":false,"given":"Rui-Chen","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Ye","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4033-8650","authenticated-orcid":false,"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8975-0444","authenticated-orcid":false,"given":"Ming-Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Ren","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Peng","family":"Zhai","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2020.3040314"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2018.0136"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01972-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2022.3157382"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.11.235"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3174257"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02328-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3066962"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560982"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386041"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152318"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560952"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-018-00269-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3123635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00066"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525601"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3168434"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110561"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3076729"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3183610"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042120"},{"key":"ref23","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref25","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560927"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206123"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561151"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196912"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3246089"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196954"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3209154"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3117790"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121757"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116063"},{"issue":"136","key":"ref36","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","first-page":"8905","article-title":"Learning fair policies in multi-objective (deep) reinforcement learning with average and discounted rewards","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Siddique"},{"key":"ref38","first-page":"14610","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref39","first-page":"11","article-title":"Dynamic weights in multi-objective deep reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Abels"},{"key":"ref40","first-page":"1","article-title":"Two-timescale networks for nonlinear value function approximation","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Chung"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/586"},{"key":"ref43","first-page":"43037","article-title":"Principled reinforcement learning with human feedback from pairwise or K-wise comparisons","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref44","first-page":"1","article-title":"Preference transformer: Modeling human preferences using transformers for RL","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Kim"},{"key":"ref45","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ouyang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910368147"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919890396"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3901\/jme.2021.07.001"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202200167"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3239306"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3325777"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10680159.pdf?arnumber=10680159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:41Z","timestamp":1752169721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10680159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":51,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3452944","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}