{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:26:56Z","timestamp":1730194016568,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1109\/adprl.2013.6614988","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T19:29:28Z","timestamp":1410377368000},"page":"47-51","source":"Crossref","is-referenced-by-count":0,"title":["A novel approach for constructing basis functions in approximate dynamic programming for feedback control"],"prefix":"10.1109","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1109\/TNNLS.2012.2217349","article-title":"Neural network based online simultaneous policy update algorithm for solving the hji equation in nonlinear h? Control","volume":"23","author":"wu","year":"2012","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"17","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"roweis","year":"2000","journal-title":"Science"},{"key":"18","first-page":"119","article-title":"Think globally, fit locally: Unsupervised learning of low dimensional manifolds","volume":"4","author":"saul","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143901"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"key":"14","article-title":"Multigrid algorithms for temporal difference reinforcement learning","author":"ziv","year":"2005","journal-title":"Proceeding of the ICML'05 Workshop on Rich Representations for Reinforcement Learning"},{"key":"11","article-title":"Explicit manifold representations for value-function approximation in reinforcement learning","author":"smart","year":"2004","journal-title":"Proceedings of the 8th Int Symp on Ai and Mathematics"},{"key":"12","article-title":"Sparse distributed memories for on-line value-based reinforcement learning","author":"ratitch","year":"2004","journal-title":"Proceedings of ECML"},{"key":"3","article-title":"Residual-gradient-based neural reinforcement learning for the optimal control of an acrobat","author":"xu","year":"2002","journal-title":"The Proceedings of the 2002 IEEE International Symposium on Intelligent Control"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2012.04.011"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"2"},{"journal-title":"Animal Intelligence","year":"1911","author":"thorndike","key":"1"},{"key":"10","article-title":"Samuel meets amarel: Automating value function approximation using global state space analysis","author":"mahadevan","year":"2005","journal-title":"Proceedings of AAAI"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"6","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":"Journal of Artificial Intelligence Research"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"4","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon gradient-based policy search","volume":"15","author":"baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9","first-page":"2169","article-title":"Proto-value functions: A laplacian framework for learning representation and control in markov decision processes","volume":"8","author":"mahadevan","year":"2007","journal-title":"Journal of Machine Learning Research"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"}],"event":{"name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2013,4,16]]},"location":"Singapore","end":{"date-parts":[[2013,4,19]]}},"container-title":["2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6596003\/6614979\/06614988.pdf?arnumber=6614988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,3]],"date-time":"2020-02-03T18:35:06Z","timestamp":1580754906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6614988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/adprl.2013.6614988","relation":{},"subject":[],"published":{"date-parts":[[2013,4]]}}}