论文标题
协方差矩阵适应地图解析
Covariance Matrix Adaptation MAP-Annealing
论文作者
论文摘要
单目标优化算法搜索有关目标的单个最高质量解决方案。质量多样性（QD）优化算法，例如协方差矩阵适应地图 - 精灵（CMA-ME），搜索有关目标相对于特定测量功能的客观和多样化的解决方案的集合。但是，CMA-ME受到了QD社区突出的三个主要局限性：过早放弃了目标，以探索探索，努力探索平坦的目标以及低分辨率档案的性能差。我们提出了一种新的质量多样性算法，协方差矩阵适应地图解析（CMA-MAE），该算法解决了所有三个限制。我们为每个限制提供了新算法的理论理由。我们的理论为我们的实验提供了信息，该实验支持理论并表明CMA-MAE实现了最先进的表现和鲁棒性。
Single-objective optimization algorithms search for the single highest-quality solution with respect to an objective. Quality diversity (QD) optimization algorithms, such as Covariance Matrix Adaptation MAP-Elites (CMA-ME), search for a collection of solutions that are both high-quality with respect to an objective and diverse with respect to specified measure functions. However, CMA-ME suffers from three major limitations highlighted by the QD community: prematurely abandoning the objective in favor of exploration, struggling to explore flat objectives, and having poor performance for low-resolution archives. We propose a new quality diversity algorithm, Covariance Matrix Adaptation MAP-Annealing (CMA-MAE), that addresses all three limitations. We provide theoretical justifications for the new algorithm with respect to each limitation. Our theory informs our experiments, which support the theory and show that CMA-MAE achieves state-of-the-art performance and robustness.
