Procedural Content Generation through Quality Diversity

Abstract

Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics. This simultaneous focus on quality and diversity with explicit metrics sets QD algorithms apart from standard single- and multi-objective evolutionary algorithms, as well as from diversity preservation approaches such as niching. These properties open up new avenues for artificial intelligence in games, in particular for procedural content generation. Creating multiple systematically varying solutions allows new approaches to creative human-AI interaction as well as adaptivity. In the last few years, a handful of applications of QD to procedural content generation and game playing have been proposed; we discuss these and propose challenges for future work.

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

References in corpus (7)

• Illuminating search spaces by mapping elites
• Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
• Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites
• Transforming Exploratory Creativity with DeLeNoX
• Adaptive Music Composition for Games
• Quality Diversity Through Surprise
• Talakat: Bullet Hell Generation through Constrained Map-Elites

Cited by in corpus (32)

• Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space
• Quality Diversity for Multi-task Optimization
• Interactive Constrained MAP-Elites: Analysis and Evaluation of the Expressiveness of the Feature Dimensions
• Fast and stable MAP-Elites in noisy domains using deep grids
• Differentiable Quality Diversity
• Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution
• Deep Surrogate Assisted MAP-Elites for Automated Hearthstone Deckbuilding
• Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains
• Analysis of Evolutionary Diversity Optimisation for Permutation Problems
• Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels
• Open-Ended Evolution for Minecraft Building Generation
• Evolving the Behavior of Machines: From Micro to Macroevolution
• Monte Carlo Elites: Quality-Diversity Selection as a Multi-Armed Bandit Problem
• Conceptual Game Expansion
• Few-shot Quality-Diversity Optimization
• Generative Design through Quality-Diversity Data Synthesis and Language Models
• Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms
• Learning to Walk Autonomously via Reset-Free Quality-Diversity
• Surrogate Infeasible Fitness Acquirement FI-2Pop for Procedural Content Generation
• Niching-based Evolutionary Diversity Optimization for the Traveling Salesperson Problem
• Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art
• The Right Variety: Improving Expressive Range Analysis with Metric Selection Methods
• Learning the Designer's Preferences to Drive Evolution
• Adaptive Procedural Task Generation for Hard-Exploration Problems
• Enhancing MAP-Elites with Multiple Parallel Evolution Strategies
• MAP-Elites with Transverse Assessment for Multimodal Problems in Creative Domains
• Level Generation with Constrained Expressive Range
• Discovering Generalizable Skills via Automated Generation of Diverse Tasks
• Self-Referential Quality Diversity Through Differential Map-Elites
• Compressing and Comparing the Generative Spaces of Procedural Content Generators
• Say "Sul Sul!" to SimSim, A Sims-Inspired Platform for Sandbox Game AI
• Policy Manifold Search for Improving Diversity-based Neuroevolution