Search-Based Procedural Content Generation: A Taxonomy and Survey

被引:304
作者
Togelius, Julian [1 ]
Yannakakis, Georgios N. [1 ]
Stanley, Kenneth O. [2 ]
Browne, Cameron [3 ]
机构
[1] IT Univ Copenhagen, DK-2300 Copenhagen, Denmark
[2] Univ Cent Florida, Dept Elect Engn & Comp Sci, Orlando, FL 32816 USA
[3] Univ London Imperial Coll Sci Technol & Med, Computat Creat Grp, London SW7 2AZ, England
基金
英国工程与自然科学研究理事会;
关键词
Computer graphics; design automation; evolutionary computation; genetic algorithms; EVOLUTIONARY COMPUTATION; NETWORKS;
D O I
10.1109/TCIAIG.2011.2148116
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The focus of this survey is on research in applying evolutionary and other metaheuristic search algorithms to automatically generating content for games, both digital and nondigital (such as board games). The term search-based procedural content generation is proposed as the name for this emerging field, which at present is growing quickly. A taxonomy for procedural content generation is devised, centering on what kind of content is generated, how the content is represented and how the quality/fitness of the content is evaluated; search-based procedural content generation in particular is situated within this taxonomy. This article also contains a survey of all published papers known to the authors in which game content is generated through search or optimisation, and ends with an overview of important open research problems.
引用
收藏
页码:172 / 186
页数:15
相关论文
共 78 条
[1]  
[Anonymous], COMPUTATIONAL INTELL
[2]  
[Anonymous], 2010, REPRESENTATIONS GENE
[3]  
[Anonymous], 2009, P 2009 IEEE S COMP I, DOI [10.1109/CIG.2009.5286482, DOI 10.1109/CIG.2009.5286482]
[4]  
[Anonymous], ARTIFACT J
[5]  
[Anonymous], 2004, AI for game developers
[6]  
[Anonymous], P SIGGRAPH
[7]  
Ashlock Daniel, 2010, 2010 IEEE Information Theory Workshop (ITW 2010), P289, DOI 10.1109/ITW.2010.5593341
[8]  
ASHLOCK D, 2006, P C EV COMP, P6728
[9]  
Ashlock DA, 2005, IEEE C EVOL COMPUTAT, P2760
[10]  
AYLETT R, 2006, P ICAPS