원문정보
국제바둑학회(구 한국바둑학회)
한국바둑학회 국제학술대회논문집
proceedings ICOB 4nd 2006 ; The 4rd International Conference on Baduk
2006.10
pp.95-111
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
This paper describes the result of applying neuro-fuzzy reasoning, which conducts Go term knowledge based on pattern 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(入) learning to test the performance. The experimental result reveals that even the simple neuro-fuzzy reasoning model can compete against TD(入) learning and it shows great potential to be applied to the real game of Go.
목차
Abstract
I. INTRODUCTION
A. What is Go?
B. Go Rules
C. Why is Computer Go so Hard?
D. fascinating Problem Domain AI Research
E. Representation of Go Knowledge
II. APPLICATION OF FUZZY REASONING TO GO
A. Neural network for supervised learning
B. Evaluation of candidate moves
C. Neuro-fuzzy controller
D. Temporal Difference learning
III. RESULTS AND DISCUSSION
A. Influence function
B. Neuro-Fuzzy controller
C. Difficulty in assessing the performance
IV. CONCLUSIONS
REFERENCES
I. INTRODUCTION
A. What is Go?
B. Go Rules
C. Why is Computer Go so Hard?
D. fascinating Problem Domain AI Research
E. Representation of Go Knowledge
II. APPLICATION OF FUZZY REASONING TO GO
A. Neural network for supervised learning
B. Evaluation of candidate moves
C. Neuro-fuzzy controller
D. Temporal Difference learning
III. RESULTS AND DISCUSSION
A. Influence function
B. Neuro-Fuzzy controller
C. Difficulty in assessing the performance
IV. CONCLUSIONS
REFERENCES