| Document Date: 2005-06-14 12:26:47
Open Document File Size: 279,46 KBShare Result on Facebook
City Yorktown / / Company IBM / Samuel / / Country United States / Netherlands / / IndustryTerm given network / controller network / tasks requiring multilayer networks / multilayer connectionist networks / feed-forward neural network / on-line using patterns / multilayer networks / bucket brigade algorithm / predictor network / game-playing network / different algorithm / search procedure / manufacturing process control / real time / compact networks / linear network / connectionist networks / realworld applications / search-based program / linear networks / incremental real-time algorithm / connectionist network / learning algorithm / sensible solution / / Person Gerald Tesauro / Thomas J. Watson / / Position teacher / feed-forward / Adaptive Heuristic Critic / representative / rst player / predictor/controller / controller / / ProvinceOrState New York / / PublishedMedium Machine Learning / / Technology learning algorithm / neural network / bucket brigade algorithm / different algorithm / related algorithm / machine learning / TD algorithm / incremental real-time algorithm / process control / /
SocialTag |
Practical Issues in Temporal Difference Learning∗ Gerald Tesauro IBM Thomas J. Watson Research Center PO Box 704, Yorktown Heights, NYUSA Abstract. This paper examines whether temporal difference methods for t