101 search results - page 4 / 21 » A Learning Architecture for the Game of Go |
88
Voted
CEC
2010
IEEE
14 years 9 months ago
2010
IEEE
—In this paper we apply Coevolutionary Temporal Difference Learning (CTDL), a hybrid of coevolutionary search and reinforcement learning proposed in our former study, to evolve s...
CIG
2006
IEEE
15 years 3 months ago
2006
IEEE
Abstract— This paper describes experiments using reinforcement learning techniques to compute pattern urgencies used during simulations performed in a Monte-Carlo Go architecture...
PPSN
2010
Springer
14 years 8 months ago
2010
Springer
Abstract. The game of Go has attracted much attention from the artificial intelligence community. A key feature of Go is that humans begin to learn on a small board, and then incr...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
DIGRA
2005
Springer
15 years 3 months ago
2005
Springer
In recent years, science education has been the focus of study and development of new gamebased learning environments. It has been argued that active and critical learning about r...