Monte Carlo Elites: Quality-Diversity Selection as a Multi-Armed Bandit Problem

TL;DR

This paper introduces a novel approach to quality-diversity evolutionary search by framing parent selection as a multi-armed bandit problem, enhancing exploration and solution quality.

Contribution

It extends MAP-Elites by applying multi-armed bandit strategies for parent selection, improving diversity and quality in search results.

Findings

Using bandit-based parent selection accelerates discovery of new regions.

Balancing exploration and exploitation yields more diverse solutions.

The approach improves archive quality across multiple testbeds.

Abstract

A core challenge of evolutionary search is the need to balance between exploration of the search space and exploitation of highly fit regions. Quality-diversity search has explicitly walked this tightrope between a population's diversity and its quality. This paper extends a popular quality-diversity search algorithm, MAP-Elites, by treating the selection of parents as a multi-armed bandit problem. Using variations of the upper-confidence bound to select parents from under-explored but potentially rewarding areas of the search space can accelerate the discovery of new regions as well as improve its archive's total quality. The paper tests an indirect measure of quality for parent selection: the survival rate of a parent's offspring. Results show that maintaining a balance between exploration and exploitation leads to the most diverse and high-quality set of solutions in three different testbeds.