플레이어 행동예측을 위한 순차예측 알고리즘의 개선

Improvement of Sequential Prediction Algorithm for Player's Action Prediction

  • 신용우 (동아방송예술대학 디지털영상과) ;
  • 정태충 (경희대학교 컴퓨터공학과)
  • 투고 : 2010.01.25
  • 심사 : 2010.04.26
  • 발행 : 2010.06.30

초록

게임은 여러 캐릭터와 상태공간을 갖고 있다. 그러므로 학습을 하는데 많은 시간이 걸린다. 본 논문에서는 강화학습 알고리즘을 이용하였다. 보상 값을 받아 캐릭터가 학습하게 하여 지능적으로 움직이게 하였다. 학습초기에는 학습속도가 느려진다. 순차예측 알고리즘을 개선하여 학습에 적용하였다. 기존 강화학습으로 구현된 게임과 비교 실험하였다. 실험결과 개선 구현된 게임의 성능이 학습속도 측면에서 30% 까지 향상됨을 알 수 있었다.

It takes quite amount of time to study a game because there are many game characters and different stages are exist for games. This paper used reinforcement learning algorithm for characters to learn, and so they can move intelligently. On learning early, the learning speed becomes slow. Improved sequential prediction method was used to improve the speed of learning. To compare a normal learning to an improved one, a game was created. As a result, improved character‘s ability was improved 30% on learning speed.

키워드

참고문헌

  1. 한국게임산업진흥원, "2008 대한민국 게임백서", 2009
  2. 신용우, "강화학습을 이용한 지능형 게임캐릭터의 제어", 인터넷정보학회논문지, 제8권 5호, pp 91-97, 2007
  3. Laramee, Francois Dominic, "A Rule-based Architecture Using Dempster-Shafer Theory", AI Game Progrmming Wisdom, Charles River Media, 2002.
  4. Mommersteeg, Fri, "Pattern Recognition with Sequential Prediction", AI Game Progrmming Wisdom, Charles River Media, 2002.
  5. Laramee, Francois Dominic, "Using N-Gram Statistical Models to Predict Player Behavior", AI Game Progrmming Wisdom, Charles River Media, 2002.
  6. Imran Ghory, "Reinforcement learning in board games.", available at http://www.cs.bris.ac.uk/Publications/Papers/2000100.pdf, 2004.
  7. Nee Jan van Eck, Michiel van Wezel., "Reinforcement Learning and its Application to Othello", available at http://www.few.eur.nl/few/people/mvanwezel/rl.othello.ejor.pdf, 2004
  8. Armand Prieditis, "Applying Model-Based Decision-Making Methods to Games: Applying the Locust AI Engine to Quake III", Game Programming Gems 6, Charles River Media, 2006.
  9. Julien Hamaide, "Short-Term Memory Modeling Using a Support Vector Machine", Game Programming Gems 6, Charles River Media, 2006.
  10. James Boer (ArenaNet), "Closest-String Matching Algorithm", Game Programming Gems 6, Charles River Media, 2006.
  11. Steve Woodcock, "Game AI : The State of the Industry", Game Developer Magazine, 2000.
  12. Steve Rabin, AI Game Programming Wisdom 2, Charles River Media, 2003
  13. Steve Rabin, AI Game Programming Wisdom, Charles River Media, 2002