Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithms

TL;DR

This paper introduces MC-AURORA, a multi-collection Quality-Diversity algorithm that uses an ensemble of auto-encoders to automatically define multiple feature descriptors, enhancing solution diversity in complex problems.

Contribution

It extends feature extraction methods to multiple representations and proposes MC-AURORA, which optimizes several solution collections with different auto-encoder-based feature descriptors.

Findings

Solutions are more diverse than single-representation methods.

Ensemble auto-encoders effectively capture complex problem features.

Approach improves exploration in multi-modal problems.

Abstract

Quality-Diversity algorithms search for large collections of diverse and high-performing solutions, rather than just for a single solution like typical optimisation methods. They are specially adapted for multi-modal problems that can be solved in many different ways, such as complex reinforcement learning or robotics tasks. However, these approaches are highly dependent on the choice of feature descriptors (FDs) quantifying the similarity in behaviour of the solutions. While FDs usually needs to be hand-designed, recent studies have proposed ways to define them automatically by using feature extraction techniques, such as PCA or Auto-Encoders, to learn a representation of the problem from previously explored solutions. Here, we extend these approaches to more complex problems which cannot be efficiently explored by relying only on a single representation but require instead a set of diverse and complementary representations. We describe MC-AURORA, a Quality-Diversity approach that optimises simultaneously several collections of solutions, each with a different set of FDs, which are, in turn, defined automatically by an ensemble of modular auto-encoders. We show that this approach produces solutions that are more diverse than those produced by single-representation approaches.