Tournament Informed Adversarial Quality Diversity

2026-01-27

AI Summary

This work addresses key challenges in traditional quality-diversity (QD) methods within adversarial settings, where fitness and behavioral characterizations often depend on opponent strategies and lack a fair mechanism for comparing solution sets. To overcome these limitations, the authors propose a variant-based tournament framework for evaluation and task selection, which dynamically balances and enhances both solution quality and behavioral diversity through two tournament-driven strategies during coevolution. This approach is the first to integrate tournament mechanisms into multi-task QD algorithms, combining behavioral characterization mapping with a six-dimensional evaluation metric to effectively mitigate fairness deficiencies and dynamic imbalances inherent in adversarial optimization. Experimental results demonstrate significant performance improvements over baseline methods across three adversarial environments: Pong, Cat-and-Mouse, and Pursuit-Evasion.

Technology Category

• Search and Optimization: Adversarial Search
• Game Theory and Economic Paradigms: Adversarial Learning
• Multiagent Systems: Adversarial Agents

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Quality diversity (QD) is a branch of evolutionary computation that seeks high-quality and behaviorally diverse solutions to a problem. While adversarial problems are common, classical QD cannot be easily applied to them, as both the fitness and the behavior depend on the opposing solutions. Recently, Generational Adversarial MAP-Elites (GAME) has been proposed to coevolve both sides of an adversarial problem by alternating the execution of a multi-task QD algorithm against previous elites, called tasks. The original algorithm selects new tasks based on a behavioral criterion, which may lead to undesired dynamics due to inter-side dependencies. In addition, comparing sets of solutions cannot be done directly using classical QD measures due to side dependencies. In this paper, we (1) use an inter-variants tournament to compare the sets of solutions, ensuring a fair comparison, with 6 measures of quality and diversity, and (2) propose two tournament-informed task selection methods to promote higher quality and diversity at each generation. We evaluate the variants across three adversarial problems: Pong, a Cat-and-mouse game, and a Pursuers-and-evaders game. We show that the tournament-informed task selection method leads to higher adversarial quality and diversity. We hope that this work will help further advance adversarial quality diversity. Code, videos, and supplementary material are available at https://github.com/Timothee-ANNE/GAME_tournament_informed.

Problem

• adversarial problems
• quality diversity
• behavioral diversity
• coevolution
• solution comparison

Innovation

• Tournament-informed selection
• Adversarial Quality Diversity
• Inter-variants tournament
• Generational Adversarial MAP-Elites
• Behavioral diversity