{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T05:20:19Z","timestamp":1740720019605,"version":"3.38.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003556","name":"Ministry of Foreign Affairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003556","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886557","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"1929-1934","source":"Crossref","is-referenced-by-count":0,"title":["A System-theoretic Note on Model-Based Actor-Critic"],"prefix":"10.1109","author":[{"given":"Simone","family":"Baroncini","sequence":"first","affiliation":[{"name":"Alma Mater Studiorum - Universita’ di Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guido","family":"Carnevale","sequence":"additional","affiliation":[{"name":"Alma Mater Studiorum - Universita’ di Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bahman","family":"Gharesifard","sequence":"additional","affiliation":[{"name":"University of California,Department of Electrical and Computer Engineering,Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Notarstefano","sequence":"additional","affiliation":[{"name":"Alma Mater Studiorum - Universita’ di Bologna,Department of Electrical, Electronic and Information Engineering,Bologna,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-015-5484-1"},{"issue":"98","key":"ref4","first-page":"1","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref6","first-page":"367","article-title":"A convergent online single time scale actor critic algorithm","volume":"11","author":"Castro","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430925"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619440"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/19M1288012"},{"key":"ref10","first-page":"17617","article-title":"A finite-time analysis of two time-scale actor-critic methods","volume":"33","author":"Wu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3078754"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3172242"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/105051606000000448"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/22M1483335"},{"key":"ref15","article-title":"Nonlinear systems","author":"Khalil","year":"2002","journal-title":"Upper Saddle River"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00076-2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF02745577"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3105652"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109451"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3187918"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","start":{"date-parts":[[2024,12,16]]},"location":"Milan, Italy","end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886557.pdf?arnumber=10886557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T08:50:35Z","timestamp":1740646235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886557","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}