arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.05352cs.NE
收藏

Multi-Emitter MAP-Elites:通过异构发射器集合提高质量、分集和收敛速度

Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters

Antoine Cully

摘要:

质量多样性(QD)优化是一个新的学习算法家族,旨在生成多样化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自适应MAP-Elites(CMA-ME)算法提出了发射器的概念,它使用预定义的启发式来驱动算法的探索。该算法被证明优于MAP-Elites,这是一种流行的QD算法,在许多应用中已经证明了有希望的结果。在本文中,我们介绍了多EMAP-Elites(ME-MAP-Elites),一种算法,直接扩展CMA-ME,提高其质量,多样性和数据效率。它利用了一组异构发射器的多样性,其中每种发射器类型以不同的方式改进优化过程。强盗算法根据当前情况动态地找到发射器的最佳选择。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)到机器人中复杂的运动任务。我们与CMA-ME和MAP-Elites的比较表明,ME-MAP-Elites在提供更多样化和更高性能的解决方案集合方面更快。此外,在不同的发射器之间没有有效的协同作用的情况下,ME-MAP-Elites相当于最好的比较算法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑