arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.10790cs.NEcs.AIcs.LG
收藏

Quality Evolvability ES:具有良好表现和多样化后代分布的进化个体

Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspring

University of York(约克大学)

Adam Katona, Daniel W. Franks, James Alfred Walker

摘要:

从深度学习的成功中得到的最重要的教训之一是,与我们手工设计的表示相比,学习的表示在任何任务中都表现得更好。然而,进化算法的进化,其目的是自动学习良好的遗传表示,得到了相对较少的关注,也许是因为它们需要大量的计算能力。最近的方法Evolvability ES允许直接选择的进化与很少的计算。然而,它只能用于解决进化性和任务性能一致的问题。我们提出了质量进化ES,同时优化任务性能和进化能力,没有这种限制的方法。我们所提出的方法质量进化有类似的动机质量多样性算法,但有一些重要的区别。虽然质量多样性的目的是找到一个多样化和表现良好的档案,但潜在的遗传遥远的个人,质量进化的目的是找到一个单一的个人与多样化和表现良好的后代分布。通过这样做,质量进化被迫发现更多的进化表示。我们证明了机器人运动控制任务的质量进化ES,类似于质量多样性的方法,可以学习速度比基于目标的方法,可以处理欺骗性的问题。

英文摘要:

One of the most important lessons from the success of deep learning is that learned representations tend to perform much better at any task compared to representations we design by hand. Yet evolution of evolvability algorithms, which aim to automatically learn good genetic representations, have received relatively little attention, perhaps because of the large amount of computational power they require. The recent method Evolvability ES allows direct selection for evolvability with little computation. However, it can only be used to solve problems where evolvability and task performance are aligned. We propose Quality Evolvability ES, a method that simultaneously optimizes for task performance and evolvability and without this restriction. Our proposed approach Quality Evolvability has similar motivation to Quality Diversity algorithms, but with some important differences. While Quality Diversity aims to find an archive of diverse and well-performing, but potentially genetically distant individuals, Quality Evolvability aims to find a single individual with a diverse and well-performing distribution of offspring. By doing so Quality Evolvability is forced to discover more evolvable representations. We demonstrate on robotic locomotion control tasks that Quality Evolvability ES, similarly to Quality Diversity methods, can learn faster than objective-based methods and can handle deceptive problems.

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。

↑