TY - JOUR
T1 - Interactive Constrained MAP-Elites
T2 - Analysis and Evaluation of the Expressiveness of the Feature Dimensions
AU - Alvarez, Alberto
AU - Dahlskog, Steve
AU - Font, Jose
AU - Togelius, Julian
N1 - Funding Information:
Thework ofAlberto Alvarez and Jose Fontwas supported by the Evolutionary World Designer project from the Crafoord Foundation.
Publisher Copyright:
© 2018 IEEE.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - In this article, we propose the interactive constrained multidimensional archive of phenotypic elites (MAP-Elites), a quality-diversity solution for game content generation, implemented as a new feature of the evolutionary dungeon designer (EDD): a mixed-initiative co-creativity tool for designing dungeons. The feature uses the MAP-Elites algorithm, an illumination algorithm that segregates the population among several cells depending on their scores with respect to different behavioral dimensions. Users can flexibly and dynamically alternate between these dimensions anytime, thus guiding the evolutionary process in an intuitive way, and then incorporate suggestions produced by the algorithm in their room designs. At the same time, any modifications performed by the human user will feed back into MAP-Elites, closing a circular workflow of constant mutual inspiration. This article presents the algorithm followed by an in-depth evaluation of the expressive range of all possible dimension combinations in several scenarios and discusses their influence in the fitness landscape and in the overall performance of the procedural content generation in the EDD.
AB - In this article, we propose the interactive constrained multidimensional archive of phenotypic elites (MAP-Elites), a quality-diversity solution for game content generation, implemented as a new feature of the evolutionary dungeon designer (EDD): a mixed-initiative co-creativity tool for designing dungeons. The feature uses the MAP-Elites algorithm, an illumination algorithm that segregates the population among several cells depending on their scores with respect to different behavioral dimensions. Users can flexibly and dynamically alternate between these dimensions anytime, thus guiding the evolutionary process in an intuitive way, and then incorporate suggestions produced by the algorithm in their room designs. At the same time, any modifications performed by the human user will feed back into MAP-Elites, closing a circular workflow of constant mutual inspiration. This article presents the algorithm followed by an in-depth evaluation of the expressive range of all possible dimension combinations in several scenarios and discusses their influence in the fitness landscape and in the overall performance of the procedural content generation in the EDD.
KW - Evaluation methods
KW - evolutionary algorithms (EAs)
KW - mixed-initiative co-creativity (MI-CC)
KW - procedural content generation (PCG)
UR - http://www.scopus.com/inward/record.url?scp=85098766850&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098766850&partnerID=8YFLogxK
U2 - 10.1109/TG.2020.3046133
DO - 10.1109/TG.2020.3046133
M3 - Article
AN - SCOPUS:85098766850
SN - 2475-1502
VL - 14
SP - 202
EP - 211
JO - IEEE Transactions on Games
JF - IEEE Transactions on Games
IS - 2
ER -