한국게임학회 논문지 (Journal of Korea Game Society)

  • 제20권6호
  • /
  • Pages.23-30
  • /
  • 2020
  • /
  • 1598-4540(pISSN)
  • /
  • 2287-8211(eISSN)
한국게임학회 (Korea Game Society)
권호 표지
DOI QR코드

DOI QR Code

강화학습에서 점진적인 심화를 이용한 고누게임의 개선

Improvement of the Gonu game using progressive deepening in reinforcement learning

  • 신용우 (동아방송예술대학교 창의융합교양학부)
  • Shin, YongWoo (Division of Creative Convergence Education, Dong-Ah Institute of Media and Arts)
  • 투고 : 2020.09.20
  • 심사 : 2020.11.15
  • 발행 : 2020.12.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

게임에서는 많은 경우의 수들을 가지고 있다. 그래서 학습을 많이 하여야 한다. 본 논문은 학습속도를 개선하기 위하여 강화학습을 이용했다. 그러나 강화학습은 많은 경우의 수들을 가지므로 학습 초기에 속도가 느려진다. 그래서 미니맥스 알고리즘을 이용하여 학습의 속도를 향상하였다. 개선된 성능을 비교하기 위해 고누게임을 제작하여 실험하였다. 실험결과는 승률은 높았지만, 동점의 결과가 발생하게 되었다. 점진적인 심화를 이용하여 게임트리를 더 탐색하여 동점인 경우를 줄이고 승률이 약 75% 향상되었다.

There are many cases in the game. So, Game have to learn a lot. This paper uses reinforcement learning to improve the learning speed. However, because reinforcement learning has many cases, it slows down early in learning. So, the speed of learning was improved by using the minimax algorithm. In order to compare the improved performance, a Gonu game was produced and tested. As for the experimental results, the win rate was high, but the result of a tie occurred. The game tree was further explored using progressive deepening to reduce tie cases and win rate has improved by about 75%.

키워드

참고문헌

  1. Korea Creative Content Agency, "White Paper On Korean Games 2019", 2019
  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. Patrick Henry Winston, "Artificial Intelligence", Addison Wesley, 1993
  7. Sukin You, "Artificial Intelligence Fundamentals", Kyohaksa, 1988
  8. Woosung Sim, "50 traditional games korean folk play", Nonghyup, 1996
  9. Woosung Sim, "Korean folk play", Dongmoonsun, 1996
  10. Steve Woodcock, "Game AI : The State of the Industry", Game Developer Magazine, 2000.
  11. Steve Rabin, AI Game Programming Wisdom 2, Charles River Media, 2003
  12. Steve Rabin, AI Game Programming Wisdom, Charles River Media, 2002