Thumbnail
Access Restriction
Open

Author Kojima, Takuya ♦ Yoshikawa, Atsushi
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Large Amount ♦ Di Cult ♦ Several Rule ♦ Strict Knowledge ♦ Deductive Approach ♦ Search Technique ♦ Game Record ♦ Evolutionary One ♦ Training Example ♦ Knowledge Acquisition ♦ Search Space ♦ Go Knowledge ♦ Tsumego Problem ♦ Heuristic Knowledge ♦ Human Expert ♦ Purpose Game Study ♦ Japanese Chess ♦ Single Training Example
Description A large amount of knowledge is considered very useful for systems playing such games as Go and Shogi (Japanese chess) which has a much larger search space than chess. Knowledge acquisition is therefore necessary for systems playing these games. This paper explains two approaches to acquire Go knowledge from game records: a deductive approach and an evolutionary one. The former is taken to acquire strict knowledge; several rules are acquired from a single training example. The latter is taken to acquire a large amount of heuristic knowledge from a large amount of training examples. TsumeGo problems are solved in order to compare the performance of the algorithm with others. 1 INTRODUCTION 1.1 PURPOSE Game studies have mainly focused on search techniques, and these techniques enable systems playing most games --- such as chess, checkers, and Othello --- to perform as well as human experts. It is very di#cult, however, for systems implemented using only search techniques to perform well...
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1999-01-01
Publisher Institution ICML Workshop on Machine Learning in Game Playing