DOI QR코드

DOI QR Code

An Implementation of Intelligent Game Characters using Neural Networks

신경망을 이용한 지능형 게임 캐릭터의 구현

  • 조병현 (국민대학교 대학원 전자정보통신공학부) ;
  • 정성훈 (한성대학교 정보공학부) ;
  • 성영락 (국민대학교 전자정보통신공학부) ;
  • 오하령 (국민대학교 전자정보통신공학부)
  • Published : 2004.12.01

Abstract

In this paper, we propose a scheme to implement intelligent game characters based on neural networks. Neural networks that implement in-telligent game character receive the action of an opponent character and the distance between them, decide intelligent character's action, and output the decision. The neural networks are trained by reinforcement learning using the scores acquired by the actions of two characters as reinforcement values. To show the usefulness of the proposed scheme, a simple fighting action game is implemented and various experiments are performed. Experimental results show that proposed intelligent characters can learn the rule of the game. The proposed scheme can be ap-plied to massively multiple online games as well as fighting action games.

본 논문에서는 신경망 기반의 지능형 게임 캐릭터를 구현하는 방법을 제안한다. 지능 캐릭터를 구현하는 신경망은 상대방 캐릭터의 행동과 상대방 캐릭터와의 거리를 입력받아 지능 캐릭터의 행동을 결정하여 출력한다 신경망은 두 캐릭터들의 행동으로 인한 점수를 강화 값으로 사용하여 강화 학습된다. 제안한 방법의 효용성을 보이기 위해서 간단한 대전 액션 게임을 구현하고 그 환경에서 여러 가지 실험을 수행하였다. 실험 견과 제안한 지능형 캐릭터가 게임의 규칙을 잘 학습할 수 있음을 보였다. 제안된 방법은 대전 게임뿐만 아니라 대규모 온라인 게임상의 캐릭터 구현에도 적용될 수 있다.

Keywords

References

  1. Darrin C. Bentivegna, Ales Ude, Christopher G. Atkeson, Gordon Cheng, 'Humanoid Robot Learning and Game Playing Using PC-Based Vision,' IEEE/RSJ Intl. Conference on Intelligent Robots and Systems EPFL, Lausanne, Switzerland, October, 2002
  2. Stephen Cass, 'Mind Games : to Beat The Competition Video Games are Getting Smarter,' IEEE Spectrum Online, Dec., 2002
  3. Daniel Fu, Ryan Houlette, Stottler Henke, 'Putting AI In Entertainment : An AI Authoring Tool for Simulation and Games,' IEEE Intelligent and Systems July/August, Vol.17, No.4, 2002 https://doi.org/10.1109/MIS.2002.1024756
  4. Daniel Johnson, Janet Wiles, 'Computer Games With Intelligence,' IEEE International Fuzzy Systems Conference, 2001
  5. Mark DeLoura, Game Programming Gems 2, Charles River Media, 2001
  6. Bernd Freisleben, 'A Neural Network that Learns to Play Five-in-a-Row,' 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems, 1995
  7. David B. Fogel, 'Using Evolutionary Programming to Create Neural Networks that are Capable of Playing Tic-Tac-Toe', Intl. Joint Confrence Networks, New York, pp.875-880, 1993
  8. 조남덕, 성백균, 김기태, '인공생명 시뮬레이션을 통한 게임 캐릭터의 전략 구현', 정보과학회 2000년 춘계학술대회, Vol.27, No.01, pp.0241-0243, April, 2000
  9. 이만재, 게임에서의 인공지능 기술, 한국정보처리학회지 Vol.9, No.3, pp.69-76, May, 2002
  10. Steve Rabin, AI Game Programming Wisdom, Charles Rivers Media, 2002
  11. Langton, C., Studying artificial life with cellular automata Physica D, Vol.22, pp.120-149, 1986 https://doi.org/10.1016/0167-2789(86)90237-X
  12. Chin-Teng Lin, C. S. George Lee, Neural Fuzzy Systems, Prentice Hall, 1996
  13. Richard. P. Lippman, An Introduction to Computing with Neural Nets, IEEE ASSP Magazine, pp.4-22, April, 1987
  14. David B. Fogel, Using Evolutionary Programming to Create Neural Networks that are Capable of Playing Tic-Tac-Toe, in Proc. 1993 Int. Joint Conf. Neural Networks(IJCNN'93), pp.875-880, 1993

Cited by

  1. An Implementation of Neural Networks Intelligent Characters for Fighting Action Games vol.14, pp.4, 2004, https://doi.org/10.5391/JKIIS.2004.14.4.383