The Journal of Information Systems (한국정보시스템학회지:정보시스템연구)

Korea Association of Information Systems (한국정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Enhanced MCTS Algorithm for Generating AI Agents in General Video Games

일반적인 비디오 게임의 AI 에이전트 생성을 위한 개선된 MCTS 알고리즘

  • 오평 (한림대학교 인터랙션 디자인학) ;
  • 김지민 (한림대학교 인터랙션 디자인학) ;
  • 김선정 (한림대학교 융합소프트웨어학과) ;
  • 홍석민 (한림대학교 광고홍보학과)
  • Received : 2016.10.04
  • Accepted : 2016.12.13
  • Published : 2016.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.

Keywords

References

  1. 곽수환, 강민철, "인공지능/다중 에이전트를 활용한 호텔 온라인 예약의 개념적 모형", 한국정보시스템학회, 단일호, pp.107-113, 2000
  2. 임정환, 김태현, 김현수, 이재기, 최형림. "인공지능/가상현실: 3차원 가상 물리 실험 시스템 개발", 한국정보시스템학회, 단일호, pp75-82, 1997.
  3. 서경민, 송해상. "효율적인 몬테 칼로 시뮬레이션을 위한 중요 샘플링 기법이 내장된 실험 틀 설계," 한국콘텐츠학회논문지, Vol. 13, No. 4, pp53-63, 2013. https://doi.org/10.5392/JKCA.2013.13.04.053
  4. Browne, C., Lucas, S., Tavener, S., Perez, D., Samothrakis, S., and Colton, S., "A Survey of Monte Carlo Tree Search Methods," IEEE Transactions on Computational Intelligence and AI in Games, Vol. 4, No. 1, pp. 1-49, 2012. https://doi.org/10.1109/TCIAIG.2012.2186810
  5. Buro, M., Long, J. R., Furtak, T. and Sturtevant, N., "Improving State Evaluation, Inference, and Search in Trick-Based Card Games," In Proceedings of the 21st International Joint Conference Artificial Intelligence (IJCAI), 2009.
  6. Chaslot, G., Bakkes, S., Szita, I. and Spronck, P., "Monte-Carlo Tree Search: A New Framework for Game AI," Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE), 2008.
  7. Frydenberg, F., Andersen, K. R., Risi, S. and Togelius, J., "Investigating MCTS Modifications in General Video Game Playing.", 2015 IEEE Conference on Computational Intelligence and Games (CIG). 2015.
  8. Garivier, A, and Moulines, E., "On Upper-Confidence Bound Policies for Non-Stationary Bandit Problems," arXiv preprint arXiv:0805.3415, 2008.
  9. Genesereth, M., Love, N. and Pell, B., "General Game Playing: Overview of the AAAI Competition," AI Magazine, Vol. 26, No. 2, pp. 62-72, 2005.
  10. Genesereth, M. and Bjornsson, Y., "The International General Game Playing Competition," AI Magazine, Vol. 34, No. 2, pp. 107-111, 2013. https://doi.org/10.1609/aimag.v34i2.2475
  11. Jacobsen, E. J., Greve, R. and Togelius, J., "Monte Mario: Platforming with MCTS," Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation (GECCO), pp. 293-300, 2014.
  12. Lara-Cabrera, R., Nogueira-Collazo, M., Cotta, C. and Fernandez-Leiva, A. J., "Game Artificial Intelligence: Challenges for the Scientific Community," In Proceedings 2st Congreso de la sociedad Espanola para las Ciencias del Videojuego Barcelona, Spain, 2015.
  13. Lee, B.-D., "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
  14. Lee, C.-S., Wang, M.-H., Chaslot, G., Hock, J.-B., Rimmel, A., Teytaud, O., Tsai, S.-R., Hsu, S.-C. and Hong, T.-P., "The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments," IEEE Transactions on Computational Intelligence and AI in Games, Vol. 1, No. 1, pp. 73-89, 2009. https://doi.org/10.1109/TCIAIG.2009.2018703
  15. Lee, C.-S., Muller, M. and Teytaud, O., "Special Issue on Monte Carlo Techniques and Computer Go," IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 4, pp. 225-228, 2010. https://doi.org/10.1109/TCIAIG.2010.2099154
  16. Perez-Liebana, D., Samothrakis, S., Togelius, J., Schaul, T., Lucas, S. M., Couetoux, A., Lee, J., Lim, C.-C. and Thompson, T., "The 2014 General Video Game Playing Competition," IEEE Transactions on Computational Intelligence and AI in Games, Vol. 8, No. 3, pp. 229-243, 2016 https://doi.org/10.1109/TCIAIG.2015.2402393
  17. Rimmel, A., Teytaud, O., Lee, C.-S., Yen, S.-J., Wang, M.-H. and Tsai, S.-R., "Current Frontiers in Computer Go," IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 4, pp. 229-238, 2010. https://doi.org/10.1109/TCIAIG.2010.2098876
  18. Ross, B., "General Video Game Playing with Goal Orientation.", Diss. Master's Thesis, University of Strathclyde, 2014.
  19. Vermorel, J. and Mohri, M., "Multi-armed Bandit Algorithms and Empirical Evaluation," European Conference on Machine Learning, Vol. 3720, pp. 437-448, 2005.