论文标题
相关性引导的无监督发现具有质量多样性算法的能力
Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms
论文作者
论文摘要
质量多样性算法提供了有效的机制，可以产生大量的多样化和高性能解决方案，这些解决方案已证明对解决下游任务具有重要作用。但是，这些算法中的大多数都依靠行为描述符来表征手工编码的多样性，因此需要有关考虑任务的先验知识。在这项工作中，我们介绍了相关性引导的无监督能力发现。一种自主性地发现针对手头任务量身定制的行为表征的质量多样性算法。特别是，我们的方法引入了一种自定义多样性指标，该指标可导致在学习行为描述符空间中感兴趣的领域附近的更高密度的解决方案。我们在模拟机器人环境中评估了我们的方法，在该机器人环境中，机器人必须根据其完整的感官数据自主发现其能力。我们在三个任务上评估了算法：导航到随机目标，以高速度向前移动并执行半滚动。实验结果表明，我们的方法设法发现了不仅多样化的解决方案的集合，而且适应了经过考虑的下游任务。
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.
