Hierarchical behavioral repertoires with unsupervised descriptors
Hierarchical behavioral repertoires with unsupervised descriptors
复制标题
具有无监督描述符的分层行为库
DOI：
10.1145/3205455.3205571
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Y. Demiris
中科院分区：
文献类型：
--
作者：
Antoine Cully;Y. Demiris
使人工代理能够自动学习复杂、多功能和高性能的行为是一个长期的挑战。本文提出了在这个方向上的一个步骤，它使用层次化的行为指令集来堆叠几个行为指令集来生成复杂的行为。这个体系结构的每个剧目都使用较低的剧目来创建复杂的行为，作为简单的行为序列，而只有最低的剧目才直接控制代理的移动。本文还介绍了一种新的自动定义行为描述符的方法，这要归功于一个组织产生的高级行为的无监督神经网络。实验表明，所提出的体系结构使机器人在学会绘制直线和圆弧后，能够在无人监督的情况下学习如何绘制数字。与传统的行为语料库相比，该体系结构将优化问题的维度降低了数量级，并为行为提供了两倍好的适应度。更重要的是，它能够在机器人之间传递知识：只需改变层次结构的最低层，就可以将为机械臂绘制数字而进化的层次结构指令集转移到类人机器人。这使得人形机器人能够画出数字，尽管它从未接受过这项任务的训练。
Enabling artificial agents to automatically learn complex, versatile and high-performing behaviors is a long-lasting challenge. This paper presents a step in this direction with hierarchical behavioral repertoires that stack several behavioral repertoires to generate sophisticated behaviors. Each repertoire of this architecture uses the lower repertoires to create complex behaviors as sequences of simpler ones, while only the lowest repertoire directly controls the agent's movements. This paper also introduces a novel approach to automatically define behavioral descriptors thanks to an unsupervised neural network that organizes the produced high-level behaviors. The experiments show that the proposed architecture enables a robot to learn how to draw digits in an unsupervised manner after having learned to draw lines and arcs. Compared to traditional behavioral repertoires, the proposed architecture reduces the dimensionality of the optimization problems by orders of magnitude and provides behaviors with a twice better fitness. More importantly, it enables the transfer of knowledge between robots: a hierarchical repertoire evolved for a robotic arm to draw digits can be transferred to a humanoid robot by simply changing the lowest layer of the hierarchy. This enables the humanoid to draw digits although it has never been trained for this task.