Dynamic Descriptor Mutations Improve Automated Quality-Diversity

van der Bank, Reece and Nitschke, Geoff (2026) Dynamic Descriptor Mutations Improve Automated Quality-Diversity, Proceedings of Genetic and Evolutionary Computation Conference (GECCO 2026), 13-17 July 2026, San José, Costa Rica, 1276-1284, ACM Press.

Text 2026-dynamic-descriptor-mutations-improve-automated-quality-diversity.pdf Download (4MB)

Abstract

Evaluating behavioral descriptors remains a major bottleneck in standard and automated Quality-Diversity optimization. Existing methods either rely on expert-crafted descriptors or fully automated ones that tend to lack interpretability and alignment with task objectives, both requiring significant resources and time. This challenge is especially pronounced in swarm systems, where descriptors must represent both individual behaviors and collective dynamics.We address this problem by introducing a Mid-Evolution behavioral descriptor mutation mechanism, where descriptors are modified during a run rather than between full re-training. This enables direct, fair comparison among differing descriptors without costly restarts, and aids in identifying descriptors that align with task objectives. Across three swarm robotics tasks (herding, block collection, and radar coverage) this Mid-Evolution mutation strategy often identifies higher-performing descriptors or eliminates weaker ones more efficiently than retraining. This approach improves evaluation efficiency and enables faster, more practical automated discovery of meaningful behavioral descriptors.

Item Type:	Conference paper
Subjects:	Computing methodologies > Artificial intelligence
Date Deposited:	15 Oct 2026 07:04
Last Modified:	15 Oct 2026 07:04
URI:	https://pubs.cs.uct.ac.za/id/eprint/1823

Actions (login required)

View Item