Using a genetic algorithm to tune first-person shooter bots

被引：50

作者：

Cole, N ^{[1
]}

Louis, SJ ^{[1
]}

Miles, C ^{[1
]}

机构：

[1] Univ Nevada, Dept Comp Sci, Evolut Comp Syst Lab, Reno, NV 89557 USA

来源：

CEC2004: PROCEEDINGS OF THE 2004 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2 | 2004年

关键词：

D O I：

10.1109/CEC.2004.1330849

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

First-person shooter robot controllers (bots) are generally rule-based expert systems written in C/C++. As such, many of the rules are parameterized with values, which are set by the software designer and finalized at compile time. The effectiveness of parameter values is dependent on the knowledge the programmer has about the game. Furthermore, parameters are non-linearly dependent on each other. This paper presents an efficient method for using a genetic algorithm to evolve sets of parameters for bots which lead to their playing as well as bots whose parameters have been tuned by a human with expert knowledge about the game's strategy. This indicates genetic algorithms as being a potentially useful method for tuning bots.

引用

页码：139 / 145

页数：7