Mix-ME: Quality-Diversity for Multi-Agent Learning
This addresses the need for adaptable solutions in multi-agent robotics, though it is an incremental extension of existing QD methods to multi-agent settings.
The paper tackled the problem of generating diverse, high-performing solutions for multi-agent systems under partial observability by introducing Mix-ME, a multi-agent variant of MAP-Elites, which often outperformed single-agent baselines in continuous control tasks.
In many real-world systems, such as adaptive robotics, achieving a single, optimised solution may be insufficient. Instead, a diverse set of high-performing solutions is often required to adapt to varying contexts and requirements. This is the realm of Quality-Diversity (QD), which aims to discover a collection of high-performing solutions, each with their own unique characteristics. QD methods have recently seen success in many domains, including robotics, where they have been used to discover damage-adaptive locomotion controllers. However, most existing work has focused on single-agent settings, despite many tasks of interest being multi-agent. To this end, we introduce Mix-ME, a novel multi-agent variant of the popular MAP-Elites algorithm that forms new solutions using a crossover-like operator by mixing together agents from different teams. We evaluate the proposed methods on a variety of partially observable continuous control tasks. Our evaluation shows that these multi-agent variants obtained by Mix-ME not only compete with single-agent baselines but also often outperform them in multi-agent settings under partial observability.