A worst-case comparison between temporal difference and residual gradient with linear function approximation
A worst-case comparison between temporal difference and residual gradient with linear function approximation
Lihong Li, 2008
Download
Abstract
(unavailable)
BibTeX Entry
@InProceedings{Li:2008, author = "Li, Lihong", title = "A worst-case comparison between temporal difference and residual gradient with linear function approximation", booktitle = "Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML 2008)", year = "2008", ISBN = "978-1-60558-205-4", editor = "Cohen, William W. and McCallum, Andrew and Roweis, Sam T.", volume = "307", series = "ACM International Conference Proceeding Series", publisher = "ACM", pages = "560--567", url = "http://www.research.rutgers.edu/~lihong/pub/Li08Worst.pdf", bib2html_rescat = "Function Approximation", }