강화된 몬테카를로 알고리즘을 활용한 강력한 삼목게임기 구현

• 영문명: Implementation of robust Tic-Tac-Toe game player, using enhanced Monte-Carlo algorithm
• 발행기관: 한국컴퓨터게임학회
• 저자명: 이병두(Byung Doo Lee)
• 간행물 정보: 『한국컴퓨터게임학회논문지』제28권 3호, 135~141쪽, 전체 7쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2015.09.30

영문 초록

Go is an extremely complex strategic board game despite its simple rules. Recently computer Go based on MCTS plays at human-master level and also has defeated top professional players with handicap games in 19×19 Go. Before implementing computer Go, in this paper we show weakness of pure MC algorithm for playing robust Tic-Tac-Toe game and present alternative method to make up the weakness. Furthermore we show how UCB algorithm works for balancing exploration and exploitation in game tree and discuss the need of a hybrid algorithm combined with UCB and strategy based MCTS, for implementing an enhanced computer Go.

목차

1. 서론

2. 관련연구

3. 본론

4. 결론 및 제언

감사의 글

참고문헌

키워드

Computer Go Tic-Tac-Toe MCTS Monte-Carlo algorithm Multi-Armed-Bandit problem UCB Upper Confidence Bounds Exploration-Exploitation dilemma