[Paper] Tournament Informed Adversarial Quality Diversity
Source: arXiv - 2601.19562v1
Overview
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 co‑evolve 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:
- Use an inter‑variants tournament to compare the sets of solutions, ensuring a fair comparison, with six measures of quality and diversity.
- 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. Results show that the tournament‑informed task selection method leads to higher adversarial quality and diversity. Code, videos, and supplementary material are available at https://github.com/Timothee-ANNE/GAME_tournament_informed.
Key Contributions
- Research area: cs.NE
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.NE.
Authors
- Timothée Anne
- Noah Syrkis
- Meriem Elhosni
- Florian Turati
- Alexandre Manai
- Franck Legendre
- Alain Jaquier
- Sebastian Risi
Paper Information
- arXiv ID: 2601.19562v1
- Categories: cs.NE
- Published: January 27, 2026
- PDF: Download PDF