인공신경망과 유전 알고리즘을 이용한 팩맨 게임 강화학습
Pacman Game Reinforcement Learning Using Artificial Neural-network and Genetic Algorithm
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (14)
- R. S. Sutton, "Reinforcement Learning :An Introduction" (2018), MIT Press
- H. H. Lee, "Deep Reinforcement Learning Application in Aerospace Filed with Unity", KSAS, Proc. of Conference, pp.522~523 (2019)
- S. Y. Jang, "Research Trends on Deep Reinforcement Learning", ETRI Electronics and Telecommunications Trends, 34(4), pp.1~14 (2019)
- 신용우, "강화학습을 이용한 지능형 게임캐릭터의 제어", 인터넷정보학회논문지, 8(5), pp.91~97 (2007), 한국인터넷정보학회
- 신용우, "플레이어 행동예측을 위한 순차예측 알고리즘의 개선", 인터넷정보학회논문지, 11(3), pp.25~32 (2010), 한국인터넷정보학회
- 박소영, "유전 알고리즘을 이용한 로봇의 최적 경로 탐색 방법 연구", 한국정밀공학회지, 35(12), pp.1147~1155 (2018), 한국정밀공학회
- J. N. Kim, "Routing Algorithm for Multiple Environment Using Genetic Algorithm", Proceedings of KIISE Conference, 38(2A), pp.333~336 (2011)
- 김지민, "유전 알고리즘을 이용한 플레이어 적응형 몬스터 생성 기법", 인터넷정보학회논문지, 18(2), pp.43~51 (2017), 한국인터넷정보학회[DOI]
- S. W. Park, "Genetic Algorithm for Game Monster Generation", Proceedings of the Korea Contents Association Conference, 4(2), pp.811~814 (2006)
- 엄상원, "진화 알고리즘을 적용한 게임 난이도 조절", 한국컴퓨터게임학회논문지, (11), pp.20~27 (2007), (사)한국컴퓨터게임학회
- 정찬호, "강화 및 진화 학습 기능을 갖는 에이전트 기반 함정 교전 시뮬레이션", 한국시뮬레이션학회 논문지, 21(4), pp.65~73 (2012), 한국시뮬레이션학회[DOI]
- Tritiya R. Arungpadang, "인공신경망과 유전알고리즘 기반의 쌍대반응표면분석에 관한 연구", 대한산업공학회지, 39(5), pp.361~366 (2013), 대한산업공학회[DOI]
- D. H. Oh, "A Study on Pathfinding in Game Environment Using Genetic Algorithm and Neural Network", Proceedings of the Korea Information Processing Society Conference, 23(2), pp.607~608 (2016)
- 박종구, "유전 알고리즘과 신경망을 이용한 RPG 게임 캐릭터의 제어", 한국게임학회 논문지, 6(2), pp.13~22 (2006), 한국게임학회