Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
This addresses a specific issue for researchers and practitioners using QD algorithms in uncertain domains like robotics, though it is incremental as it builds on existing methods.
The paper tackles the problem of Quality-Diversity algorithms producing degenerate solutions in noisy environments by introducing ARIA, a plug-and-play module that improves solution reproducibility, resulting in at least a 50% enhancement in archive quality and descriptor space coverage.
Quality-Diversity (QD) algorithms are designed to generate collections of high-performing solutions while maximizing their diversity in a given descriptor space. However, in the presence of unpredictable noise, the fitness and descriptor of the same solution can differ significantly from one evaluation to another, leading to uncertainty in the estimation of such values. Given the elitist nature of QD algorithms, they commonly end up with many degenerate solutions in such noisy settings. In this work, we introduce Archive Reproducibility Improvement Algorithm (ARIA); a plug-and-play approach that improves the reproducibility of the solutions present in an archive. We propose it as a separate optimization module, relying on natural evolution strategies, that can be executed on top of any QD algorithm. Our module mutates solutions to (1) optimize their probability of belonging to their niche, and (2) maximize their fitness. The performance of our method is evaluated on various tasks, including a classical optimization problem and two high-dimensional control tasks in simulated robotic environments. We show that our algorithm enhances the quality and descriptor space coverage of any given archive by at least 50%.