IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Pacman Game Reinforcement Learning Using Artificial Neural-network and Genetic Algorithm

인공신경망과 유전 알고리즘을 이용한 팩맨 게임 강화학습

  • Park, Jin-Soo (Korea National University of Transportation(KNUT)) ;
  • Lee, Ho-Jeong (Korea National University of Transportation(KNUT)) ;
  • Hwang, Doo-Yeon (Korea National University of Transportation(KNUT)) ;
  • Cho, Soosun (Korea National University of Transportation(KNUT))
  • Received : 2020.07.28
  • Accepted : 2020.09.08
  • Published : 2020.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Genetic algorithms find the optimal solution by mimicking the evolution of natural organisms. In this study, the genetic algorithm was used to enable Pac-Man's reinforcement learning, and a simulator to observe the evolutionary process was implemented. The purpose of this paper is to reinforce the learning of the Pacman AI of the simulator, and utilize genetic algorithm and artificial neural network as the method. In particular, by building a low-power artificial neural network and applying it to a genetic algorithm, it was intended to increase the possibility of implementation in a low-power embedded system.

Keywords

References

  1. R.S. Sutton, A.G. Barto, Reinforcement Learning :An Introduction, 2nd Edition, MIT Press, Cambridge, MA, 2018.
  2. H.H. Lee, T.Y. Kim, M.J. Choi, "Deep Reinforcement Learning Application in Aerospace Filed with Unity," KSAS, Proc. of Conference, pp. 522-523, 2019 (in Korean).
  3. S.Y. Jang, H.J. Yoon, N.S. Park, J.K. Yun, Y.S. Son, “Research Trends on Deep Reinforcement Learning,” ETRI Electronics and Telecommunications Trends, Vol. 34, No. 4, pp. 1-14, 2019(in Korean).
  4. Y.W. Shin, “Control of Intelligent Characters Using Reinforcement Learning,” JICS, Vol. 8, No. 5, pp. 91-97, 2007 (in Korean).
  5. Y.W. Shin, T.C. Chung, “Improvement of Sequential Prediction Algorithm for Player's Action Prediction,” JICS, Vol. 11, No. 3, pp. 25-32, 2010 (in Korean).
  6. S.Y. Park, P.W. Park, J.M. Kim, J.H. Borm, S.W. Lee, “A Study on Searching Optimal Path for Robot Using Genetic Algorithm,” J. Korean Soc. Precis. Eng., Vol. 35, No. 12, pp. 1147-1155, 2018 (in Korean). https://doi.org/10.7736/KSPE.2018.35.12.1147
  7. J.N. Kim, H.T. Kim, C.W. Ahn, "Routing Algorithm for Multiple Environment Using Genetic Algorithm," Proceedings of KIISE Conference, 38(2A), pp. 333-336, 2011 (in Korean).
  8. J.M. Kim, S.J. Kim, S.M. Hong, "Players Adaptive Monster Generation Technique Using Genetic Algorithm," JIC, Vol. 18, No. 2, pp. 43-51, 2017 (in Korean).
  9. S.W. Park, W.H. Lee, "Genetic Algorithm for Game Monster Generation," Proceedings of the Korea Contents Association Conference, Vol. 4, No. 2, pp. 811-814, 2006 (in Korean).
  10. T.Y. Kim, J.S. Choi, "Game Difficulty Controlling Using Evolutionary Algorithm," Journal of the Korean Society for Computer Game, No. 11, pp. 20-27, 2007 (in Korean).
  11. C.H. Jung, C.Y. Park, S.D. Chi, J. Kim, "The Battle Warship Simulation of Agent-based with Reinforcement and Evolutionary Learning," Journal of the Korea Society for Simulation, Vol. 21, Issue 4, pp. 65-73, 2012 (in Korean). https://doi.org/10.9709/JKSS.2012.21.4.065
  12. T.R. Arungpadang, Y.J. Kim, "A Study on Dual Response Approach Combining Neural Network and Genetic Algorithm," Journal of the Korean Institute of Industrial Engineers, Vol. 39, No. 5, pp. 361-366, 2013 (in Korean). https://doi.org/10.7232/JKIIE.2013.39.5.361
  13. D.H. Oh, "A Study on Pathfinding in Game Environment Using Genetic Algorithm and Neural Network," Proceedings of the Korea Information Processing Society Conference, Vol. 23, No. 2, pp. 607-608, 2016 (in Korean).
  14. O.K. Kwun, J.K. Park, "Control of RPG Game Characters using Genetic Algorithm and Neural Network," Journal of Korea Game Society, Vol. 6, No. 2, pp. 13-22, 2006 (in Korean).