Browse > Article
http://dx.doi.org/10.7583/JKGS.2020.20.1.57

Build reinforcement learning AI process for cooperative play with users  

Jung, Won-Joe (Dept. of R&D, GoodgameStudio Corp)
Abstract
The goal is to implement AI using reinforcement learning, which replaces the less favored Supporter in MOBA games. ML_Agent implements game rules, environment, observation information, rewards, and punishment. The experiment was divided into P and C group. Experiments were conducted to compare the cumulative compensation values and the number of deaths to draw conclusions. In group C, the mean cumulative compensation value was 3.3 higher than that in group P, and the total mean number of deaths was 3.15 lower. performed cooperative play to minimize death and maximize rewards was confirmed.
Keywords
AI; Reinforcement learning; Machine learning; Unity3D;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 S.Y.Jang, H.J.Yoon, N.S.Park, J.K.Yun, Y.S.Son, "Research Trends on Deep Reinforcement Learning", Electronics and Telecommunications Trends, Vol.34, No.4, pp. 1-14, 2019 August
2 Seong-Chan Hong "Artificial Intelligence Design and Implementation of Fighting Game Using Reinforcement Learning", KwangWoon university graduate school, 2019
3 Mun-seok Gang "Online Reinforcement Learning That Learns Fast in a Maze Environment", MyongJi university graduate school, 2000 June
4 Dong-eun Yang "A Study of Tennis game AI through DQN", Korea university graduate school of Computer & Information Technology , 2017 December
5 Unity, "Introducing: Unity Machine Learning Agents Toolkit", 2017 September 19
6 B.H. Cho, C.J. Park, "Research Trends in Game AI", Electronics and Telecommunications Research Institut, 2008 August
7 Gyeong-wan Guk "AI technology and application cases by industry", BioIN, 2019 March
8 Jung-Hyun Kim, "Analysis of preference of the AOS playing character based on personality types", Journal of Next-generation Convergence Information Services Technology, Vol.3, No.1, pp. 61-70, 2014 May