DOI QR코드

DOI QR Code

An improvement of the learning speed through Influence Map on Reinforcement Learning

영향력분포도를 이용한 강화학습의 학습속도개선

  • Shin, Yong-Woo (Division of Creative Convergence Education, Dong-Ah Institute of Media and Arts)
  • 신용우 (동아방송예술대학교 창의융합교양학부)
  • Received : 2017.07.04
  • Accepted : 2017.08.17
  • Published : 2017.08.20

Abstract

It takes quite amount of time to study a board game because there are many game characters and many state spaces are exist for board games. Therefore, game must do learning long. But, there is weakness with reinforcement learning. On Learning early, the learning speed becomes slow. If there were equal result that both are considered to be best ones during the course of learning stage, Heuristic which utilizes learning of problem area of Jul-Gonu was used to improve the speed of learning. To compare a normal character to an improved one, a board game was created, and then they fought against each other. As a result, improved character's ability was improved on learning speed.

보드게임은 많은 수의 말들과 상태공간을 갖고 있다. 그러므로 게임은 학습을 오래하여야 한다. 그러나 강화학습은 학습초기에 학습속도가 느려지는 단점이 있다. 그러므로 학습 도중에 동일한 최선 값이 있을 때, 영향력분포도를 고려한 문제 영역 지식을 활용한 휴리스틱을 사용해 학습의 속도 향상을 시도하였다. 기존 구현된 말과 개선 구현된 말을 비교하기 위해 보드게임을 제작하였다. 그래서 일방공격형 말과 승부를 하게 하였다. 실험 결과 개선 구현된 말의 성능이 학습속도 측면에서 향상됨을 알 수 있었다.

Keywords

References

  1. Korea Creative Content Agency, "Content Industry Trend Analysis Report for 4Q 2016 (Game Industry)", 2017
  2. Richard Sutton, Andrew G. Barto, "Reinforcement Learning :An Introduction", MIT Press, Cambridge, MA, 1998.
  3. Imran Ghory, "Reinforcement learning in board games.", available at http://www.cs.bris.ac.uk/Publications/Papers/2000100.pdf, 2004.
  4. 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
  5. Yongwoo Shin, "Artificial Engine Development through Reinforcement Learning on Jul-Gonu Game ", Journal of Internet Computing and Services, Vol 10, No 1, pp93-99, 2009
  6. Yongwoo Shin, Tae-Choong Chung, "An Improvement of the learning speed through Improved Reinforcement Learning on Jul-Gonu Game", Journal of Internet Computing and Services, Vol 10, No 3, pp9-15, 2009
  7. Woosung Sim, "50 traditional games Korean folk play", Nonghyup, 1996
  8. Woosung Sim, "Korean folk play", Dongmoonsun, 1996
  9. Tozour, Paul, "Influence Mapping", Game Programming Gems 2, Charles River, 2001
  10. Laramee, Francois Dominic, "A Rule-based Architecture Using Dempster-Shafer Theory", AI Game Programming Wisdom, Ed. Steve Rabin, Charles River Media, 2002.
  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