The Computational Intelligence of Computer Go
Computer Go programs have received some recent attention in AI (Artificial Intelligence) research. One reason is that the Computer Go provides a platform that is both interesting enough to attract people; and complex enough to design the challengeable game AI for successful gameplay. This paper describes AMAF (All-Moves-As-First) algorithm used in the Computer Go. Moreover, we also introduce the improving simulation with domain knowledge. In the end, the experimental result from the Computer Go are presented to demonstrate the effectiveness and efficiency; and the limitation of these methods are discussed, together with possible directions for extending the work towards producing better Computer Go AI.
Computer Go AI AMAF domain knowledge of Computer Go
Bin Wu
School of Software Engineering,Beijing University of Posts and Telecommunications,Beijing, China
国际会议
北京
英文
603-605
2011-08-24(万方平台首次上网日期,不代表论文的发表时间)