KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

GreedyUCB1 based Monte-Carlo Tree Search for General Video Game Playing Artificial Intelligence

일반 비디오 게임 플레이 인공지능을 위한 GreedyUCB1기반 몬테카를로 트리 탐색

  • Received : 2015.03.31
  • Accepted : 2015.06.08
  • Published : 2015.08.15
⟨ Previous Next ⟩

Abstract

Generally, the existing Artificial Intelligence (AI) systems were designed for specific purposes and their capabilities handle only specific problems. Alternatively, Artificial General Intelligence can solve new problems as well as those that are already known. Recently, General Video Game Playing the game AI version of General Artificial Intelligence, has garnered a large amount of interest among Game Artificial Intelligence communities. Although video games are the sole concern, the design of a single AI that is capable of playing various video games is not an easy process. In this paper, we propose a GreedyUCB1 algorithm and rollout method that were formulated using the knowledge from a game analysis for the Monte-Carlo Tree Search game AI. An AI that used our method was ranked fourth at the GVG-AI (General Video Game-Artificial Intelligence) competition of the IEEE international conference of CIG (Computational Intelligence in Games) 2014.

보통의 인공지능 시스템은 특정 작업을 수행하기 위해 설계되며, 해당 작업만을 수행하는 능력을 가진다. 그에 반해 인공 일반지능이란 설계 당시 목표로 한 작업만이 아니라 새로 접하는 다양한 문제에도 대응할 수 있는 인공지능을 의미한다. 최근 게임 인공지능 분야의 일반지능 문제인 General Video Game Playing에 대한 관심이 높아지고 있다. 비디오 게임으로 범위가 제한되었지만, 다양한 형태의 비디오 게임을 플레이 할 수 있는 단일 인공지능을 설계하는 것은 상당히 도전적인 문제이다. 본 논문에서는 Monte-Carlo Tree Search를 이용하는 기존 비디오 게임을 위한 인공 일반지능을 개선하는 방법에 대해 기술한다. 여기서는 UCB1 알고리즘을 문제에 적합하도록 개선한 GreedyUCB1과 게임 분석을 통해 얻은 지식을 활용한 Rollout 방법을 제안한다. 제안한 방법으로 개발된 인공지능은 국제 학술대회인 IEEE Computational Intelligence in Games의 2014년 인공지능 경진 대회에 출전하여 4위의 성적을 보였다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. M. Genesereth, N. Love, and B. Pell, "General Game Playing: Overview of the AAAI Competition," AI Mag., Vol. 26, No. 2, p. 62, Mar. 2005.
  2. J. Levine, C. B. Congdon, M. Ebner, G. Kendall, S. M. Lucas, R. Miikkulainen, T. Schaul, and T. Thompson, "General Video Game Playing," Artif. Comput. Intell. Games, Vol. 6, pp. 77-83, Dec. 2013.
  3. D. Perez, S. Samothrakis, J. Togelius, T. Schaul, and S. Lucas (2014), The GVG-AI Competition [Online]. Available: http://www.gvgai.net/ (downloaded 2015, Mar. 15)
  4. C. B. Browne, E. Powley, D. Whitehouse, S. M. Lucas, P. I. Cowling, P. Rohlfshagen, S. Tavener, D. Perez, S. Samothrakis, and S. Colton, "A Survey of Monte Carlo Tree Search Methods," IEEE Trans. Comput. Intell. AI Games, Vol. 4, No. 1, pp. 1-43, Mar. 2012. https://doi.org/10.1109/TCIAIG.2012.2186810
  5. P. Auer, N. Cesa-Bianchi, and P. Fischer, "Finitetime Analysis of the Multiarmed Bandit Problem," Mach. Learn., Vol. 47, No. 2-3, pp. 235-256, May 2002. https://doi.org/10.1023/A:1013689704352
  6. GGP Homepage, [Online]. Available: http://games.stanford.edu/(downloaded 2015, Feb. 28)
  7. M. G. Bellemare, Y. Naddaf, J. Veness, and M. Bowling, "The Arcade Learning Environment: An Evaluation Platform for General Agents," J. Artif. Intell. Res., Vol. 47, pp. 253-279, Jun. 2013.
  8. M. Gendron-Bellemare, "Fast, Scalable Algorithms for Reinforcement Learning in High Dimensional Domains," University of Alberta, 2013.
  9. M. Hausknecht, P. Khandelwal, R. Miikkulainen, and P. Stone, "HyperNEAT-GGP: A HyperNEATbased Atari General Game Player," Proc. of the 14th Int. Conf. on Genetic and Evol. Comput. Conf., pp. 217-224, Jul. 2012.
  10. V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, "Playing Atari with Deep Reinforcement Learning," Proc. of the Deep Learning. Neural Information Processing Systems Workshop, Dec. 2013.
  11. T. Schaul, "An Extensible Description Language for Video Games," IEEE Trans. Comput. Intell. AI Games, Vol. 6, No. 4, pp. 325-331, Oct., 2014. https://doi.org/10.1109/TCIAIG.2014.2352795
  12. S. M. Lucas, S. Samothrakis, and D. Perez, "Fast Evolutionary Adaptation for Monte Carlo Tree Search," Application of Evolutionary Computation, pp. 349-360, Springer, Berlin, 2014.
  13. D. Perez, S. Samothrakis, and S. Lucas, "Knowledge-based Fast Evolutionary MCTS for General Video Game Playing," Proc. of the 2014 IEEE Conf. on Comput. Intell. and Games (CIG), pp. 1-8, Oct., 2014.