Learning behaviour-performance maps with meta-evolution

Learning behaviour-performance maps with meta-evolution
复制标题

具有元进化的学习行为-表现图

DOI:
10.1145/3377930.3390181
复制
发表时间:
2020
期刊:
--
影响因子:
--
通讯作者:
Bossens D
Bossens D
中科院分区:
--
文献类型:
--
作者:
Bossens D

文献摘要

参考文献

被引文献

相似文献

MAP-Elites质量多样性算法在机器人领域取得了成功,因为它可以创建一组行为多样的解决方案,这些解决方案随后可用于适应,例如对意外损害的适应。在MAP-Elites中,行为空间的选择对于适应,在看不见的环境中恢复性能至关重要,因为它定义了解决方案的多样性。目前的做法是手工编码的一组行为特征,然而,考虑到可能的行为表现地图的大空间,设计师不知道先验的行为功能最大化地图的适应潜力。我们介绍了一种新的元进化算法,发现那些行为特征,最大限度地提高未来的适应。所提出的方法应用协方差矩阵自适应进化策略来进化一个群体的行为性能图,以最大限度地提高元适应功能,奖励适应。该方法将MAP-Elites找到的解决方案存储在数据库中,从而可以快速构建新的行为-性能映射。为了评估这个系统,我们研究了RHex机器人的步态,因为它适应了一系列的损害持续在其腿上。当与用户定义的行为空间的MAP精英相比,我们证明了元进化系统学习高性能的步态,或没有损害注入到机器人。
The MAP-Elites quality-diversity algorithm has been successful in robotics because it can create a behaviorally diverse set of solutions that later can be used for adaptation, for instance to unanticipated damages. In MAP-Elites, the choice of the behaviour space is essential for adaptation, the recovery of performance in unseen environments, since it defines the diversity of the solutions. Current practice is to hand-code a set of behavioural features, however, given the large space of possible behaviour-performance maps, the designer does not know a priori which behavioural features maximise a map's adaptation potential. We introduce a new meta-evolution algorithm that discovers those behavioural features that maximise future adaptations. The proposed method applies Covariance Matrix Adaptation Evolution Strategy to evolve a population of behaviour-performance maps to maximise a meta-fitness function that rewards adaptation. The method stores solutions found by MAP-Elites in a database which allows to rapidly construct new behaviour-performance maps on-the-fly. To evaluate this system, we study the gait of the RHex robot as it adapts to a range of damages sustained on its legs. When compared to MAP-Elites with user-defined behaviour spaces, we demonstrate that the meta-evolution system learns high-performing gaits with or without damages injected to the robot.
Talakat:通过受限的地图精英生成弹幕地狱
DOI: --
发表时间: 2018
期刊: 2018 Genetic and Evolutionary Computation Conference (GECCO
影响因子: --
作者:
Khalifa, Ahmed;Lee, Scott;Nealen, Andy;Togelius, Julian
通讯作者: Togelius, Julian
DOI: 10.1145/3205455.3205571
发表时间: 2018
期刊: Proceedings of the Genetic and Evolutionary Computation Conference
影响因子: --
作者:
Antoine Cully;Y. Demiris
通讯作者: Y. Demiris
DOI: --
发表时间: 2016-04
期刊: ArXiv
影响因子: --
作者:
N. Hansen
通讯作者: N. Hansen
外科医生和艾滋病毒感染者的回复
DOI: --
发表时间: 1990
期刊:
影响因子: --
作者:
L. Gostin
通讯作者: L. Gostin
结合 MAP-Elite 和增量进化来生成哺乳动物四足机器人的步态
DOI: 10.1007/978-3-319-77538-8_48
发表时间: 2018
期刊: Comparative Biochemistry and Physiology Part C: Comparative Pharmacology
影响因子: --
作者:
Jørgen Nordmoen;K. Ellefsen;K. Glette
通讯作者: K. Glette