{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T05:39:28Z","timestamp":1729661968378,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1109\/ijcnn.2014.6889527","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T14:30:33Z","timestamp":1410359433000},"page":"3657-3662","source":"Crossref","is-referenced-by-count":1,"title":["A Kalman filter-based actor-critic learning approach"],"prefix":"10.1109","author":[{"given":"Bin","family":"Wang","sequence":"first","affiliation":[]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.946","article-title":"Efficient reinforcement learning using recursive least-squares methods","volume":"16","author":"xu","year":"2002","journal-title":"J Artif Intell Res"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42042-9_31"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"13","article-title":"Dual heuristic dynamic programming for nonlinear discrete-time uncertain systems with state delay","author":"wang","year":"2013","journal-title":"Neurocomputing"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-013-1110-y"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252630"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553504"},{"key":"21","first-page":"289","article-title":"Off-policy learning with eligibility traces: A survey","volume":"15","author":"geist","year":"2014","journal-title":"J Mach Learn Res"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8134-8"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927543"},{"key":"23","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1613\/jair.3077","article-title":"Kalman temporal differences","volume":"39","author":"geist","year":"2010","journal-title":"J Artif Intell Res"},{"key":"24","first-page":"644","article-title":"Approximate kalman filter Q-learning for continuous state-space MDPs","author":"tripp","year":"2013","journal-title":"Proc 11th Conf Uncertainty Artificial Intell"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"journal-title":"An introduction to the Kalman filter","year":"1995","author":"welch","key":"26"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1115\/1.3426922"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"2","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"1"},{"key":"7","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12 Proceedings of the 1999 Conference"},{"journal-title":"On-line Q-learning using connectionist systems","year":"1994","author":"rummery","key":"6"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247418"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.801727"}],"event":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2014,7,6]]},"location":"Beijing","end":{"date-parts":[[2014,7,11]]}},"container-title":["2014 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6880678\/6889358\/06889527.pdf?arnumber=6889527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:47:59Z","timestamp":1602690479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6889527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2014.6889527","relation":{},"subject":[],"published":{"date-parts":[[2014,7]]}}}