| Document Date: 2006-01-11 02:39:56
Open Document File Size: 309,55 KBShare Result on Facebook
City TD / / Company Russell / IBM / / / IndustryTerm reinforcement learning algorithm / neural network / multilayer neural network / neural networks / larger and larger networks / few successful applications / heuristic doubling algorithm / possible applications / learning algorithm / / Person Hans Berliner / Malcolm Davis / Kent Goulding / Bill Robertie / Sylvester Robertie / Paul Magriel / / / Position teacher / weak advanced player / rated player / human player / backgalmnon player / player / / PublishedMedium Machine Learning / / SportsEvent the World Cup / the 1992 World Cup / World Cup / / Technology learning algorithm / neural network / heuristic doubling algorithm / Machine Learning / reinforcement learning algorithm / / URL www.aaai.org / /
SocialTag |
TD-Gammon, A Self-teaching Backgammon Program, Achieves Master-Level Play