{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:26:33Z","timestamp":1767986793042,"version":"3.49.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10156372","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T17:48:03Z","timestamp":1688406483000},"page":"3382-3388","source":"Crossref","is-referenced-by-count":5,"title":["Continuous-Time Policy Optimization"],"prefix":"10.23919","author":[{"given":"Guojian","family":"Zhan","sequence":"first","affiliation":[{"name":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingliang","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,School of Mechanical Engineering,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengbo Eben","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,State Key Lab of Automotive Safety and Energy, School of Vehicle and Mobility,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Neuro-dynamic programming","author":"Bertsekas","year":"1996"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/9780203749319"},{"key":"ref3","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/103"},{"key":"ref5","first-page":"11 639","article-title":"Adaptive checkpoint adjoint method for gradient estimation in neural ode","volume-title":"International Conference on Machine Learning","author":"Zhuang"},{"key":"ref6","first-page":"16 689","article-title":"Interpolation technique to speed up gradients propagation in neural odes","volume":"33","author":"Daulbaev","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"1054","article-title":"Faster policy learning with continuous-time gradients","author":"Ainsworth","year":"2021","journal-title":"Learning for Dynamics and Control"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.134"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/int.22466"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2014.1325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.11.115"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27590-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483388"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669260"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-19-7784-8","volume-title":"Reinforcement learning for sequential decision-making and control","author":"Li","year":"2023"}],"event":{"name":"2023 American Control Conference (ACC)","location":"San Diego, CA, USA","start":{"date-parts":[[2023,5,31]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10156372.pdf?arnumber=10156372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T11:06:25Z","timestamp":1709291185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":16,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10156372","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}