Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites

Abstract

We propose the use of quality-diversity algorithms for mixed-initiative game content generation. This idea is implemented as a new feature of the Evolutionary Dungeon Designer, a system for mixed-initiative design of the type of levels you typically find in computer role playing games. The feature uses the MAP-Elites algorithm, an illumination algorithm which divides the population into a number of cells depending on their values along several behavioral dimensions. Users can flexibly and dynamically choose relevant dimensions of variation, and incorporate suggestions produced by the algorithm in their map designs. At the same time, any modifications performed by the human feed back into MAP-Elites, and are used to generate further suggestions.

arXiv comment8 pages, Accepted and to appear in proceedings of 2019 IEEE Conference on Games, COG 2019

References in corpus (1)

• DATA Agent

Cited by in corpus (18)

• Procedural Content Generation through Quality Diversity
• Interactive Constrained MAP-Elites: Analysis and Evaluation of the Expressiveness of the Feature Dimensions
• Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization
• Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters
• Analysis of Evolutionary Diversity Optimisation for Permutation Problems
• Designer Modeling through Design Style Clustering
• Lode Encoder: AI-constrained co-creativity
• Generative Design through Quality-Diversity Data Synthesis and Language Models
• Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
• Evaluating Mixed-Initiative Procedural Level Design Tools using a Triple-Blind Mixed-Method User Study
• Niching-based Evolutionary Diversity Optimization for the Traveling Salesperson Problem
• Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms
• The Right Variety: Improving Expressive Range Analysis with Metric Selection Methods
• The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers
• Learning the Designer's Preferences to Drive Evolution
• Boosting Mixed-Initiative Co-Creativity in Game Design: A Tutorial
• MAP-Elites with Transverse Assessment for Multimodal Problems in Creative Domains
• Compressing and Comparing the Generative Spaces of Procedural Content Generators