proceedings ICOB 4nd 2006 ; The 4rd International Conference on Baduk (2006.10)바로가기
페이지
pp.95-111
저자
Byung-Doo Lee
언어
영어(ENG)
URL
https://www.earticle.net/Article/A27275
원문정보
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