当前位置: X-MOL 学术arXiv.cs.NE › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters
arXiv - CS - Neural and Evolutionary Computing Pub Date : 2020-07-10 , DOI: arxiv-2007.05352
Antoine Cully

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, MAP-Elites is a simple yet powerful approach that has shown promising results in numerous applications. In this paper, we introduce a novel algorithm named Multi-Emitter MAP-Elites (ME-MAP-Elites) that improves the quality, diversity and convergence speed of MAP-Elites. It is based on the recently introduced concept of emitters, which are used to drive the algorithm's exploration according to predefined heuristics. ME-MAP-Elites leverages the diversity of a heterogeneous set of emitters, in which each emitter type is designed to improve differently the optimisation process. Moreover, a bandit algorithm is used to dynamically find the best emitter set 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 MAP-Elites and existing approaches using emitters show that ME-MAP-Elites is faster at providing collections of solutions that are significantly more diverse and higher performing. Moreover, in the rare cases where no fruitful synergy can be found between the different emitters, ME-MAP-Elites is equivalent to the best of the compared algorithms.

中文翻译:

多发射器 MAP-Elite:使用异构发射器集提高质量、多样性和收敛速度

质量多样性 (QD) 优化是一个新的学习算法系列,旨在生成多样化和高性能解决方案的集合。在这些算法中,MAP-Elites 是一种简单而强大的方法,已在众多应用中显示出有希望的结果。在本文中,我们介绍了一种名为 Multi-Emitter MAP-Elites (ME-MAP-Elites) 的新算法,该算法提高了 MAP-Elites 的质量、多样性和收敛速度。它基于最近引入的发射器概念,用于根据预定义的启发式驱动算法的探索。ME-MAP-Elites 利用一组异构发射器的多样性,其中每种发射器类型都旨在以不同的方式改进优化过程。而且,强盗算法用于根据当前情况动态找到最佳发射器集。我们评估了 ME-MAP-Elites 在六项任务上的性能,从标准优化问题(100 维)到机器人中的复杂运动任务。我们与 MAP-Elites 和使用发射器的现有方法的比较表明,ME-MAP-Elites 在提供更加多样化和更高性能的解决方案集合方面更快。此外,在极少数情况下,在不同发射器之间找不到富有成效的协同作用,ME-MAP-Elites 相当于比较算法中最好的。我们与 MAP-Elites 和使用发射器的现有方法的比较表明,ME-MAP-Elites 在提供更加多样化和更高性能的解决方案集合方面更快。此外,在极少数情况下,在不同发射器之间找不到富有成效的协同作用,ME-MAP-Elites 相当于比较算法中最好的。我们与 MAP-Elites 和使用发射器的现有方法的比较表明,ME-MAP-Elites 在提供更加多样化和更高性能的解决方案集合方面更快。此外,在极少数情况下,在不同发射器之间找不到富有成效的协同作用,ME-MAP-Elites 相当于比较算法中最好的。
更新日期:2020-07-13
down
wechat
bug