{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:30:56Z","timestamp":1730341856776,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T00:00:00Z","timestamp":1654646400000},"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":[[2022,6,8]]},"DOI":"10.23919\/acc53348.2022.9867217","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:24:10Z","timestamp":1662409450000},"page":"2124-2129","source":"Crossref","is-referenced-by-count":4,"title":["Quasi-Newton Iteration in Deterministic Policy Gradient"],"prefix":"10.23919","author":[{"given":"Arash Bahari","family":"Kordabad","sequence":"first","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hossein","family":"Nejatbakhsh Esfahani","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Cai","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastien","family":"Gros","sequence":"additional","affiliation":[{"name":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Natural policy gradient primal-dual method for constrained markov decision processes","volume":"33","author":"ding","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"159","article-title":"Quasi newton temporal difference learning","author":"givchi","year":"2015","journal-title":"Asian Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2010.05.025"},{"journal-title":"Combining system identification with reinforcement learning-based mpc","year":"2020","author":"martinsen","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2913768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"key":"ref17","first-page":"480","article-title":"Emotional learning based intelligent controller for mimo peripheral milling process","volume":"6","author":"bahari kordabad","year":"2020","journal-title":"Journal of Computational and Applied Mechanics"},{"key":"ref18","first-page":"1019","article-title":"Covariant policy search","author":"bagnell","year":"2003","journal-title":"Proceedings of the International Joint Conference on Artifical Intelligence"},{"journal-title":"Numerical Optimization","year":"2006","author":"nocedal","key":"ref4"},{"key":"ref3","first-page":"i?387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0"},{"key":"ref6","first-page":"8055","article-title":"Approximate newton methods for policy search in markov decision processes","volume":"17","author":"furmston","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref5","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41188-6_7"},{"journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL","year":"2019","author":"bertsekas","key":"ref2"},{"key":"ref1","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref9","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2022 American Control Conference (ACC)","start":{"date-parts":[[2022,6,8]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2022,6,10]]}},"container-title":["2022 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9866948\/9867142\/09867217.pdf?arnumber=9867217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:39:55Z","timestamp":1664829595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9867217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,8]]},"references-count":18,"URL":"https:\/\/doi.org\/10.23919\/acc53348.2022.9867217","relation":{},"subject":[],"published":{"date-parts":[[2022,6,8]]}}}