{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:34:58Z","timestamp":1774456498639,"version":"3.50.1"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,8]]},"DOI":"10.1109\/ijcnn.2013.6706755","type":"proceedings-article","created":{"date-parts":[[2014,1,10]],"date-time":"2014-01-10T15:08:44Z","timestamp":1389366524000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["Solutions to finite horizon cost problems using actor-critic reinforcement learning"],"prefix":"10.1109","author":[{"given":"Ivo","family":"Grondman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarangapani","family":"Jagannathan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"13","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426427"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(98)00301-9"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.905848"},{"key":"2","author":"powell","year":"2010","journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1177\/0037549708098120"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-18324-9"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5707071"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2012.6357855"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/72.536307"},{"key":"4","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"8","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/978-3-642-23780-5_41","article-title":"Lagrange dual decomposition for finite horizon markov decision processes","author":"furmston","year":"2011","journal-title":"Proceedings of the 2011 European Conference on Machine Learning and Knowledge Discovery in Databases"}],"event":{"name":"2013 International Joint Conference on Neural Networks (IJCNN 2013 - Dallas)","location":"Dallas, TX, USA","start":{"date-parts":[[2013,8,4]]},"end":{"date-parts":[[2013,8,9]]}},"container-title":["The 2013 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6691896\/6706705\/06706755.pdf?arnumber=6706755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T05:20:13Z","timestamp":1565068813000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6706755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2013.6706755","relation":{},"subject":[],"published":{"date-parts":[[2013,8]]}}}