论文标题
多发射机地图 - 精英：通过异构发射器组合提高质量，多样性和收敛速度
Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters
论文作者
论文摘要
质量多样性（QD）优化是一种新的学习算法系列，旨在生成各种和高性能解决方案的集合。在这些算法中，最近引入的协方差矩阵适应地图 - 精英（CMA-ME）算法提出了发射器的概念，该算法使用了预定义的启发式方法来推动该算法的探索。该算法被证明超过了地图 - 精英，这是一种流行的QD算法，在许多应用中都显示出有希望的结果。在本文中，我们介绍了多发射机地图 - 精英（ME-MAP-ELITE），该算法直接扩展了CMA-ME并提高了其质量，多样性和数据效率。它利用了一组异构发射器的多样性，其中每种发射极类型以不同的方式改善优化过程。强盗算法根据当前情况动态找到最佳的发射器选择。我们评估了M-MAP-Elites在六个任务上的性能，从标准优化问题（在100个维度）到机器人技术中的复杂运动任务。我们与CMA-ME和MAP-ELITE的比较表明，Me-Map-eLites在提供多种多样和更高性能的解决方案方面的收集速度更快。此外，如果在不同的发射器之间找不到富有成果的协同作用，则ME-MAP-Elites等同于比较算法中最好的。
Quality-Diversity (QD) optimisation is a new family of learning algorithms that aims at generating collections of diverse and high-performing solutions. Among those algorithms, the recently introduced Covariance Matrix Adaptation MAP-Elites (CMA-ME) algorithm proposes the concept of emitters, which uses a predefined heuristic to drive the algorithm's exploration. This algorithm was shown to outperform MAP-Elites, a popular QD algorithm that has demonstrated promising results in numerous applications. In this paper, we introduce Multi-Emitter MAP-Elites (ME-MAP-Elites), an algorithm that directly extends CMA-ME and improves its quality, diversity and data efficiency. It leverages the diversity of a heterogeneous set of emitters, in which each emitter type improves the optimisation process in different ways. A bandit algorithm dynamically finds the best selection of emitters depending on the current situation. We evaluate the performance of ME-MAP-Elites on six tasks, ranging from standard optimisation problems (in 100 dimensions) to complex locomotion tasks in robotics. Our comparisons against CMA-ME and MAP-Elites show that ME-MAP-Elites is faster at providing collections of solutions that are significantly more diverse and higher performing. Moreover, in cases where no fruitful synergy can be found between the different emitters, ME-MAP-Elites is equivalent to the best of the compared algorithms.
