Effect of Noisy Fitness in Real-Time Strategy Games Player Behaviour Optimisation Using Evolutionary Algorithms

作     者：Antonio M. Mora Antonio Fernndez-Ares Juan J. Merelo Pablo García-Snchez Carlos M. Fernandes 

作者机构：Computer Architecture and Technology DepartmentUniversity of Granada Institute for Systems and RoboticsTechnical University of Lisbon 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2012年第27卷第5期

页      面：1007-1023页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 081104[工学-模式识别与智能系统] 08[工学] 081302[工学-建筑设计及其理论] 0835[工学-软件工程] 0813[工学-建筑学] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Andalusian Autonomous Government (Junta de Andalucía) under Project No. P08-TIC-03903, Ministerio de Ciencia e Innovación under Project No. TIN2011-28627-C04-02 Foundation for Science and Technology(FCT) of Portugal (ISR/IST plurianual funding) through the PIDDAC Program funds FCT,Ministério da Ci encia e Tecnologia, for his Research Fellowship under Grant No. SFRH/BPD/66876/2009 

主　　题：real-time strategy game genetic algorithm noisy fitness player behaviour optimisation parameter adaptation 

摘      要：This paper investigates the performance and the results of an evolutionary algorithm （EA） specifically designed for evolving the decision engine of a program （which, in this context, is called bot） that plays Planet Wars. This game, which was chosen for the Google Artificial Intelligence Challenge in 2010, requires the bot to deal with multiple target planets, while achieving a certain degree of adaptability in order to defeat different opponents in different scenarios. The decision engine of the bot is initially based on a set of rules that have been defined after an empirical study, and a genetic algorithm （GA） is used for tuning the set of constants, weights and probabilities that those rules include, and therefore, the general behaviour of the bot. Then, the bot is supplied with the evolved decision engine and the results obtained when competing with other bots （a bot offered by Google as a sparring partner, and a scripted bot with a pre-established behaviour） are thoroughly analysed. The evaluation of the candidate solutions is based on the result of non-deterministic battles （and environmental interactions） against other bots, whose outcome depends on random draws as well as on the opponents＇ actions. Therefore, the proposed GA is dealing with a noisy fitness function. After analysing the effects of the noisy fitness, we conclude that tackling randomness via repeated combats and reevaluations reduces this effect and makes the GA a highly valuable approach for solving this problem.