{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:08:43Z","timestamp":1780463323633,"version":"3.54.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"International Science and Technology Cooperation Program of China","award":["2019YFE0100200"],"award-info":[{"award-number":["2019YFE0100200"]}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["51575293"],"award-info":[{"award-number":["51575293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSF, China","doi-asserted-by":"publisher","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Geekplus Technology Company Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1109\/tnnls.2022.3175595","type":"journal-article","created":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T21:43:12Z","timestamp":1653946992000},"page":"466-478","source":"Crossref","is-referenced-by-count":25,"title":["Model-Based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9346-1858","authenticated-orcid":false,"given":"Baiyu","family":"Peng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genjin","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congsheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0689-0510","authenticated-orcid":false,"given":"Yang","family":"Guan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Mu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enxin","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294300"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-021-00151-3"},{"key":"ref8","first-page":"1","article-title":"Model-ensemble trust-region policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kurutach"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2516565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2574363"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.12.009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2560018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref17","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref18","first-page":"1","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref19","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tessler"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2022.01.003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.2979635"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683748"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2016.03.005"},{"issue":"1","key":"ref26","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0255(99)00081-X"},{"key":"ref28","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid Lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref29","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2016.2602087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225701"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2008.4738806"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1989.4790464"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/02331934.2019.1643344"},{"key":"ref36","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML)","author":"Deisenroth"},{"key":"ref37","volume-title":"Reinforcement Learning for Decision-making and Control","author":"Li","year":"2022"},{"key":"ref38","first-page":"612","article-title":"Constrained differential optimization","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Platt"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2015.0205"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/12832.003.0015"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10381493\/09785377.pdf?arnumber=9785377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:46:23Z","timestamp":1705016783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9785377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":41,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3175595","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]}}}