{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:13:54Z","timestamp":1729653234312,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/isic.2002.1157857","type":"proceedings-article","created":{"date-parts":[[2003,6,25]],"date-time":"2003-06-25T21:03:42Z","timestamp":1056575022000},"page":"758-763","source":"Crossref","is-referenced-by-count":1,"title":["Residual-gradient-based neural reinforcement learning for the optimal control of an acrobot"],"prefix":"10.1109","author":[{"family":"Xin Xu","sequence":"first","affiliation":[]},{"family":"Han-gen He","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"593","article-title":"Psedolinearization of the acrobat’ using spline functions","author":"bortoff","year":"1992","journal-title":"Proc of the IEEE Conf on Decision and Control"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/37.341864"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref13","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Advances in NIPS 12"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114728"},{"key":"ref3","article-title":"Gradient descent for general reinforcement learning","author":"baird","year":"1999","journal-title":"Advances in NeuralInformation Processing Systems 11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","first-page":"1038","article-title":"Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding","author":"sutton","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623497331063"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement Learning: A Survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref9","first-page":"669","article-title":"Nonlinear controllers for non-integratable systems: the acrobat example","author":"hauser","year":"1990","journal-title":"Proc of American Control Conference"}],"event":{"name":"International Symposium on Intelligent Control","acronym":"ISIC-02","location":"Vancouver, BC, Canada"},"container-title":["Proceedings of the IEEE Internatinal Symposium on Intelligent Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8228\/25379\/01157857.pdf?arnumber=1157857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,23]],"date-time":"2020-03-23T22:52:55Z","timestamp":1585003975000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1157857\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/isic.2002.1157857","relation":{},"subject":[]}}