종료된 삼목게임의 전략 적합도 인식을 위한 진화신경망 모델
Evolutionary neural network model for recognizing strategic fitness of a finished Tic-Tac-Toe game
0
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
Evolutionary computation is a powerful tool for developing computer games. Back-propagation neural network(BPNN) was proved to be a universal approximator and genetic algorithm(GA) a global searcher. The game of Tic-Tac-Toe, also known as Naughts and Crosses, is often used as a test bed for testing new AI algorithms. We tried to recognize the strategic fitness of a finished Tic-Tac-Toe game when the parameters, such as a sequence of moves, its game depth and result, are provided. To implement this, we've constructed an evolutionary model using GA with back-propagation NNs(GANN). The experimental results revealed that GANN, in the very long training time, converges very slowly; however, performance of recognizing the strategic fitness does not meet we expected and, further, increase of the population size does not significantly contribute to the performance of GANN.
Abstract
Evolutionary computation is a powerful tool for developing computer games. Back-propagation neural network(BPNN) was proved to be a universal approximator and genetic algorithm(GA) a global searcher. The game of Tic-Tac-Toe, also known as Naughts and Crosses, is often used as a test bed for testing new AI algorithms. We tried to recognize the strategic fitness of a finished Tic-Tac-Toe game when the parameters, such as a sequence of moves, its game depth and result, are provided. To implement this, we've constructed an evolutionary model using GA with back-propagation NNs(GANN). The experimental results revealed that GANN, in the very long training time, converges very slowly; however, performance of recognizing the strategic fitness does not meet we expected and, further, increase of the population size does not significantly contribute to the performance of GANN.
참고문헌 (12)
- 최영욱, "삼목 게임에서의 최선의 수순", 한국컴퓨터게임학회논문지, 27(3), pp.11~16 (2014), (사)한국컴퓨터게임학회
- 이병두, "한중일 프로바둑기사 포석 분석", 한국컴퓨터게임학회논문지, 26(4), pp.17~26 (2013), (사)한국컴퓨터게임학회
- 이병두, "주성분분석을 활용한 한국 프로바둑기사 포석 인식", 한국컴퓨터게임학회논문지, 26(2), pp.73~80 (2013), (사)한국컴퓨터게임학회
- 이병두, "유전 알고리즘을 이용한 삼목 게임 전략 분석", 한국게임학회 논문지, 14(6), pp.39~48 (2014), 한국게임학회[DOI]
- 이병두, "삼목 게임에 적용된 몬테카를로 트리탐색", 한국게임학회 논문지, 14(3), pp.47~54 (2014), 한국게임학회[DOI]
- 안일준, "유전 알고리즘과 게임 트리를 병합한 오목 인공지능 설계 및 GPU 기반 병렬 처리 기법", 정보과학회논문지 : 시스템 및 이론, 37(2), pp.66~75 (2010), 한국정보과학회
- A. Bhatt, "In Search of No-loss Strategies for the Game of Tic-Tac-Toe using a Customized Genetic Algorithm", GECCO'08(Genetic and Evolutionary Computation Conference 2008), pp.889~896 (2008)
- S. H. Ling, "Playing Tic-Tac-Toe Using Genetic Neural Network with Double Transfer Functions", Journal of Intelligent Learning Systems and Applications, 3, pp.37~44 (2011)
- Byung-Doo Lee, "Artificial Intelligence Go" (2011), Books Holic
- "Evaluation Function Based Monte-Carlo LOA" (2014)[URL]
- "On the Genetic Evolution of a Perfect Tic-Tac-Toe Strategy" (2014)[URL]
- "Genetic Algorithm" (2014)[URL]