{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:16:42Z","timestamp":1768281402023,"version":"3.49.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["L257002"],"award-info":[{"award-number":["L257002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tnnls.2025.3605362","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:32:58Z","timestamp":1757439178000},"page":"312-326","source":"Crossref","is-referenced-by-count":0,"title":["Bicriteria Policy Optimization for High-Accuracy Reinforcement Learning"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-4860","authenticated-orcid":false,"given":"Guojian","family":"Zhan","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4532-7467","authenticated-orcid":false,"given":"Xiangteng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feihong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Letian","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the College of Artificial Intelligence, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3348489"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"issue":"9","key":"ref3","first-page":"1499","article-title":"Key technologies of brain-inspired decision and control intelligence for autonomous driving systems","volume":"45","author":"Li","year":"2023","journal-title":"Automot. Eng."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3196167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3537087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/int.22466"},{"key":"ref11","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2024.09.056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926614"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10156372"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201521"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.05.049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2012.2198057"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1201\/9780203749319"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342038"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104161"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-405163-8.00007-7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.7249\/r366"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0559-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVCI59596.2023.10397281"},{"key":"ref30","first-page":"35300","article-title":"Leveraging offline data in online reinforcement learning","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Wagenmaker"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3395626"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11339259\/11153798.pdf?arnumber=11153798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:02:04Z","timestamp":1768255324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":31,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3605362","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}