{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:08:39Z","timestamp":1773511719476,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB2502901"],"award-info":[{"award-number":["2022YFB2502901"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Tsinghua University-Toyota Joint Research Center for AI Technology of Automated Vehicle","doi-asserted-by":"publisher","award":["U20A20334"],"award-info":[{"award-number":["U20A20334"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3511670","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T22:38:26Z","timestamp":1733956706000},"page":"11049-11063","source":"Crossref","is-referenced-by-count":1,"title":["Conformal Symplectic Optimization for Stable Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-472X","authenticated-orcid":false,"given":"Yao","family":"Lyu","sequence":"first","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4923-3633","authenticated-orcid":false,"given":"Shengbo","family":"Eben Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility and the College of Artificial Intelligence, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3697-1576","authenticated-orcid":false,"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"}]},{"given":"Letian","family":"Tao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8516-1185","authenticated-orcid":false,"given":"Qing","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0370-177X","authenticated-orcid":false,"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9333-7416","authenticated-orcid":false,"given":"Keqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3163816"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2024.3364428"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3275732"},{"key":"ref10","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IDAP.2017.8090299"},{"key":"ref15","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref17","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1614734113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.103.053304"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1142\/9789813272880_0022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/abf5d4"},{"issue":"73","key":"ref23","first-page":"1","article-title":"Optimization with momentum: Dynamical, control-theoretic, and symplectic perspectives","volume":"22","author":"Muehlebach","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01777-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-015-0062-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/abcaee"},{"key":"ref27","first-page":"4148","article-title":"The marginal value of adaptive gradient methods in machine learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Wilson"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.4171\/owr\/2006\/14"},{"key":"ref31","first-page":"9793","article-title":"Adaptive methods for nonconvex optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zaheer"},{"key":"ref32","article-title":"Improving generalization performance by switching from Adam to SGD","author":"Shirish Keskar","year":"2017","journal-title":"arXiv:1712.07628"},{"key":"ref33","first-page":"1","article-title":"Incorporating Nesterov momentum into Adam","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Dozat"},{"key":"ref34","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100096"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3329823"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1002\/9781118029176","volume-title":"Approximate Dynamic Programming: Solving the Curses of Dimensionality: Second Edition","author":"Powell","year":"2011"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10792938.pdf?arnumber=10792938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:58:32Z","timestamp":1749059912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10792938\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3511670","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}