Journal of Korea Game Society (한국게임학회 논문지)

Korea Game Society (한국게임학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Tic-Tac-Toe Game Strategies using Genetic Algorithm

유전 알고리즘을 이용한 삼목 게임 전략 분석

  • Lee, Byung-Doo (Dept. of Baduk Studies, Division of Sports Science, Sehan University)
  • 이병두 (세한대학교 체육학부 바둑학과)
  • Received : 2014.11.12
  • Accepted : 2014.12.11
  • Published : 2014.12.20
Download PDF
⟨ Previous Next ⟩

Abstract

Go is an extremely complex strategy board game despite its simple rules. By using MCTS, the computer Go programs with handicap game have been defeated human Go professionals. MCTS is based on the winning rate estimated by MC simulation rather than strategy concept. Meanwhile Genetic algorithm equipped with an adequate fitness function can find out the best solutions in the game. The game of Tic-Tac-Toe, also known as Naughts and Crosses, is one of the most popular games. We tried to find out the best strategy in the game of Tic-Tac-Toe. The experimental result showed that Genetic algorithm enables to find efficient strategies and can be applied to other board games such as Go and chess.

바둑은 단순한 규칙에도 불구하고 매우 복잡한 전략보드 게임이다. 몬테카를로 트리탐색을 이용하여 컴퓨터 바둑 프로그램들이 접바둑으로 프로기사를 제압해 왔다. 몬테카를로 트리탐색은 전략의 개념보다는 몬테카를로 시뮬레이션에 의해 계산된 승률에 근간을 한다. 반면에 적절한 적합도 함수로 된 유전 알고리즘은 게임 내 최적 해를 찾아낼 수 있다. 삼목 게임(또는 ${\bigcirc}{\times}$게임)은 가장 대중적인 게임 중의 하나이다. 저자는 삼목 게임에서의 최선의 전략을 찾고자 했다. 실험 결과로 유전 알고리즘은 효율적인 전략들을 찾을 수가 있으며, 바둑과 서양장기와 같은 여타 보드게임들에 적용할 수 있음을 보였다.

Keywords

References

  1. B.D Lee, "Monte-Carlo Tree Search Applied to the game of Tic-Tac-Toe", Journal of Korea Game Society, Vol. 14, No. 3, pp. 47-54, 2014. https://doi.org/10.7583/JKGS.2014.14.3.47
  2. B.D. Lee and J.W. Park, "Applying Principal Component Analysis to Go Openings", Journal of Korea Game Society, Vol. 13, No. 2, pp. 59-70, 2013. https://doi.org/10.7583/JKGS.2013.13.2.59
  3. B.D. Lee, "The best move sequence in playing Tic-Tac-Toe game", Journal of The Korean Society for Computer Game, Vol. 27, No. 3, pp. 11-16, 2014.
  4. B.D. Lee, "Analysis of Korean, Chinese and Japanese Pro Go Player's Openings", Journal of Korean Society for Computer Game, Vol.26, No.4, pp. 17-26, 2013.
  5. B.D. Lee, "Comparison of LDA and PCA for Korean Pro Go Player's Opening Recognition", Journal of Korea Game Society, Vol.13, No.4, pp. 15-24, 2013.
  6. B.D. Lee, "Korean Pro Go Player's Opening Recognition Using PCA", Journal of Korean Society for Computer Game, Vol.26, No.2, pp. 228-233, 2013.
  7. B.D. Lee, "Applying Neuro-fuzzy Reasoning to Go Opening Games", Journal of Korea Game Society, Vol.9, No.6, pp. 117-126, 2009.
  8. Wikipedia, "Computer Go", from http://en.wikipedia.org/wiki/Computer_Go, 2014.
  9. M.H.M. Winands and Y. Brornsson, "Evaluation Function Based Monte-Carlo LOA", from http://www.ru.is/∼yngvi/pdf/WinandsB09.pdf, 2014.
  10. G. Hochmuth, "On the Genetic Evolution of a Perfect Tic-Tac-Toe Strategy", from http://www.genetic-programming.org/sp2003/Hochmuth.pdf, 2014.
  11. A. Bhatt, P. Varshney and K. Deb, "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.
  12. Wikipedia, "Genetic Algorithm", from http://ko.wikipedia.org/wiki/%EC%9C%A0%E C%A0%84_%EC%95%8C%EA%B3%A0%EB %A6%AC%EC%A6%98, 2014.
  13. I.J. Ahn and I.K. Park, "Design of Omok AI using Genetic Algorithm and Game Trees and Their Parallel Processing on the CPU", Journal of the Korea Information Science Society, Vol. 37, No. 2, pp. 66-75, 2010.
  14. S.H. Ling and H.K. Lam, "Playing Tic-Tac-Toe Using Genetic Neural Network with Double Transfer Functions", Journal of Intelligent Learning Systems and Applications, Vol. 3, pp. 37-44, 2011. https://doi.org/10.4236/jilsa.2011.31005