An improvement of the learning speed through Improved Reinforcement Learning on Jul-Gonu Game
Yong-Woo Shin, TaeChoong Chung · Journal of Internet Computing and services · 2009
Abstract It takes quite amount of time to study a board game because there are many game chara cters and different stages are exist for board games. Also, the opponent is not just a single charac ter that means it is not one on one game, but group vs. group. That is why strategy is needed, and therefore applying o ptimum learning is a must. This paper used reinforcement learning algorithm for board characters to learn, and so they can move intelligently. If there were equal result that both are considered to be best ones duri ng 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 oth er. As a result, improved character’s ability was far more improved on learning speed. ☞ keyword : Reinforcement Learning, Jul-Gonu, Gonu, Learning Spee d, Game 강화학습 , 줄고누 , 고누 , 학습속도 , 게임 1. 서 론 온라인게임의 보급이 많아지고 장르별로도 다양하게 롤플레잉이나 시뮬레이션 장르뿐이 아니라, 캐쥬얼게임 과 스포츠게임등 다양한 장르의 게임이 보급되고 있다. 또한 3D 게임의 제작 또한 많아지고 있다. 과거에는 엔진과 게임프로그램으로 나누어 개발하던 시점에서 이제는 좀 더 세