The Application of Neuro-fuzzy Reasoning to the Opening Game of 19x19 Go

B.D. Lee, H.W. Guesgen (New Zealand), J. Baltes (Canada), and S.-H. Jeong (Korea)

Keywords

NeuroFuzzy Reasoning, Temporal Difference Learning,Neural Network, Distance Transform, Computer Go

Abstract

This paper describes the result of applying neuro-fuzzy rea soning, which conducts Go term knowledge based on pat tern knowledge, to the opening game of Go. We discuss the implementation of neuro-fuzzy reasoning for deciding the best next move to proceed through the opening game. We also let neuro-fuzzy reasoning play against TD() learning to test the performance. The experimental result reveals that simple neuro-fuzzy reasoning performs considerably better than TD learning and it shows great potential to be applied to the real game of Go.

Important Links:



Go Back