Dominated Novelty Search: Rethinking Local Competition in Quality-Diversity

2025-02-01

AI Summary

Existing quality-diversity (QD) algorithms rely on fixed grids or explicit archives to enforce local competition, necessitating pre-specified boundaries and exhibiting high sensitivity to hyperparameters—leading to poor generalization in high-dimensional and unsupervised settings. To address this, we propose a novel paradigm termed *dynamic fitness transformation*, which decouples local competition into a fitness re-calibration process grounded in multi-objective dominance relations, thereby eliminating the need for structured archives and manually defined boundaries. Our method integrates an archive-free genetic framework with adaptive behavioral space mapping, achieving full parameter self-adaptation. Evaluated on standard QD benchmarks, it consistently outperforms state-of-the-art methods, demonstrating superior robustness and performance in high-dimensional spaces and unguided learning tasks.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Game Theory and Economic Paradigms: Adversarial Learning
• Machine Learning: Evolutionary Learning

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Quality-Diversity is a family of evolutionary algorithms that generate diverse, high-performing solutions through local competition principles inspired by natural evolution. While research has focused on improving specific aspects of Quality-Diversity algorithms, surprisingly little attention has been paid to investigating alternative formulations of local competition itself -- the core mechanism distinguishing Quality-Diversity from traditional evolutionary algorithms. Most approaches implement local competition through explicit collection mechanisms like fixed grids or unstructured archives, imposing artificial constraints that require predefined bounds or hard-to-tune parameters. We show that Quality-Diversity methods can be reformulated as Genetic Algorithms where local competition occurs through fitness transformations rather than explicit collection mechanisms. Building on this insight, we introduce Dominated Novelty Search, a Quality-Diversity algorithm that implements local competition through dynamic fitness transformations, eliminating the need for predefined bounds or parameters. Our experiments show that Dominated Novelty Search significantly outperforms existing approaches across standard Quality-Diversity benchmarks, while maintaining its advantage in challenging scenarios like high-dimensional and unsupervised spaces.

Problem

• Quality-Diversity Algorithms
• Fixed Grids/Archives
• High-Dimensional Spaces

Innovation

• Dominated Novelty Search
• Quality Diversity Algorithm
• High-dimensional Space