Quality-Diversity algorithms provide efficient mechanisms to generate large
collections of diverse and high-performing solutions, which have shown to be
instrumental for solving downstream tasks. However, most of those algorithms
rely on a behavioural descriptor to characterise the diversity that is
hand-coded, hence requiring prior knowledge about the considered tasks. In this
work, we introduce Relevance-guided Unsupervised Discovery of Abilities; a
Quality-Diversity algorithm that autonomously finds a behavioural
characterisation tailored to the task at hand. In particular, our method
introduces a custom diversity metric that leads to higher densities of
solutions near the areas of interest in the learnt behavioural descriptor
space. We evaluate our approach on a simulated robotic environment, where the
robot has to autonomously discover its abilities based on its full sensory
data. We evaluated the algorithms on three tasks: navigation to random targets,
moving forward with a high velocity, and performing half-rolls. The
experimental results show that our method manages to discover collections of
solutions that are not only diverse, but also well-adapted to the considered
downstream task.

提出了一种基于 Relevance-guided Unsupervised Discovery of Abilities 的 Quality-Diversity 算法，可以自动发现适用于任务的行为描述符，并在模拟机器人环境中验证了算法的有效性。