한국IT서비스학회지 (Journal of Information Technology Services)

한국IT서비스학회 (Korea Society of IT Services)
권호 표지
DOI QR코드

DOI QR Code

기계학습 알고리즘 기반의 인공지능 장기 게임 개발

Development of Artificial Intelligence Janggi Game based on Machine Learning Algorithm

  • 장명규 (국민대학교 컴퓨터공학부) ;
  • 김영호 (국민대학교 컴퓨터공학부) ;
  • 민동엽 (국민대학교 컴퓨터공학부) ;
  • 박기현 (국민대학교 컴퓨터공학부) ;
  • 이승수 (국민대학교 컴퓨터공학부) ;
  • 우종우 (국민대학교 컴퓨터공학부)
  • 투고 : 2017.07.19
  • 심사 : 2017.10.28
  • 발행 : 2017.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Researches on the Artificial Intelligence has been explosively activated in various fields since the advent of AlphaGo. Particularly, researchers on the application of multi-layer neural network such as deep learning, and various machine learning algorithms are being focused actively. In this paper, we described a development of an artificial intelligence Janggi game based on reinforcement learning algorithm and MCTS (Monte Carlo Tree Search) algorithm with accumulated game data. The previous artificial intelligence games are mostly developed based on mini-max algorithm, which depends only on the results of the tree search algorithms. They cannot use of the real data from the games experts, nor cannot enhance the performance by learning. In this paper, we suggest our approach to overcome those limitations as follows. First, we collects Janggi expert's game data, which can reflect abundant real game results. Second, we create a graph structure by using the game data, which can remove redundant movement. And third, we apply the reinforcement learning algorithm and MCTS algorithm to select the best next move. In addition, the learned graph is stored by object serialization method to provide continuity of the game. The experiment of this study is done with two different types as follows. First, our system is confronted with other AI based system that is currently being served on the internet. Second, our system confronted with some Janggi experts who have winning records of more than 50%. Experimental results show that the rate of our system is significantly higher.

키워드

참고문헌

  1. Bang, J.S., D.C. Lee, S.H. Seo, Y.J. Kim, H.J. Lee, and W.H. Son, "Trends of VR/AR Game Technology", Electronics and Telecommunications Trends, Vol.31, No.1, 2016, 146-156. (방준성, 이동춘, 서상현, 김용준, 이헌주, 손욱호, "VR/AR 게임기술 동향", 전자통신동향분석, 제31권, 제1호, 2016, 146-156.
  2. Browne, C., E. Powley, D. Whitehouse, S. Lucas, P. Cowling, and P. Rohlfshagen, "A Survey of Monte Carlo Tree Search Methods", IEEE Transactions on Computational Intelligence and AI in Games, Vol.4, No.1, 2012, 1-49. https://doi.org/10.1109/TCIAIG.2012.2186810
  3. Cho, B.H. and C.J. Park, "Research Trends in Game AI", Electronics and Tellecommunications Trends, Vol.23, No.4, 2008, 115-121. (조병헌, 박창준, "게임 인공지능 연구동향", 전자 통신동향분석, 제23권, 제4호, 2008, 115-121.)
  4. Fan, Y.F., X.J. Bai, R.Y. Lui, and S. Xing, "The Research of Chinese Chess Based on Database with Self Learning", Proceedings of the Ninth International Conference on Machine Learning and Cybernetics, 2010, 319-322.
  5. Feinberg, E. and A. Shwartz, Handbook of Markov Decision Processes, Kluwer, Boston, MA, 2002.
  6. Ingram, J. and J. Mcgregor, "A Look at the Future of Autonomous Connected Vehicle Systems", Proceedings of International Conference on Software Engineering and Data Engineering, Vol.23, 2015, 162-177.
  7. Kim, S.W., S.W. Ahn, and H.S. Choo, "Artificial Intelligence of AlphaGo", SPRi Issue Report, 2016-001, Vol.1, 2016. (김석원, 안성원, 추형석, "AlphaGo의 인공지능", SPRi Issue Report, 제2016-001호, 제1호, 2016.)
  8. Kulsinskas, A., C. Balan, N. Bukdahl, and A. Brooks, "Augmentation of Board Games Using Smartphones", Lecture Notes in Computer Science, Vol.2015, No.9177, 2015, 483-492.
  9. Mandziuk, J., Knowledge-Free and Learning-based Methods in Intelligent Game Playing, Springer, Berlin, 2010.
  10. Millington, I. and J. Funge, Artificial Intelligence for Games, Elsevier Inc., Berlington, MA, 2009.
  11. Ong, C., H. Quek, K. Tan, and A. Tay, "Dis covering Chinese Chess Strategies through Co-evolutionary Approaches," IEEE Symposium on Computational Intelligence and Games, 2007, 360-367.
  12. Park, D.S., "ICT Convergence Industry Outlook in the Era of Artificial Intelligence," 2017 ICT Industry Outlook Conference, 2016. (박대수, "인공지능 시대의 ICT융합 산업 전망", 2017 ICT산업 전망 컨퍼런스, 2016.)
  13. Park, H.S. and K.J. Kim, "Latest Research Trend of Artificial Intelligence in Games", Journal of Korean Institute of Information Scientists and Engineers(KIISE), Vol.31, No.7, 2013, 8-15. (박현수, 김경중, "게임 인공지능 최신 연구동향", 정보과학회지, 제31권, 제7호, 2013, 8-15.)
  14. Rivest, R., "Game Tree Searching by Min/Max Approximation", Artificial Intelligence, Vol. 34, No.1, 1987, 77-96. https://doi.org/10.1016/0004-3702(87)90004-X
  15. Robilliard, D. and C. Fonlupt, "Towards Human-Competitive Game Playing for Complex Board Games with Genetic Programming", Lecture Notes in Computer Science, Vol.2016, No.9554, 2015, 123-135.
  16. Spencer, P. and J. Oommen, "Novel AI Strategies for Multi-Player Games at Intermediate Board States", Lecture Notes in Computer Science, Vol.2015, No.9101, 2015, 33-42.
  17. Silver, D., A. Huang, C. Maddison, A. Guez, L. Sifre, and G. Driessche, "Mastering the Game of Go with Deep Neural Networks and Tree Search", Nature, Vol.529, 2016, 484-489. https://doi.org/10.1038/nature16961
  18. Wu, G. and J. Tao, "Chinese Chess Algorithm Design and Implementation in the Computer Games", Proceedings of the 35th Chinese Control Conference, 2016, 10380-10384.