Vision-guided behavior acquisition of a mobile robot by multi-layered reinforcement learning
Vision-guided behavior acquisition of a mobile robot by multi-layered reinforcement learning
复制标题
通过多层强化学习视觉引导移动机器人行为获取
DOI：
10.1109/iros.2000.894637
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
M. Asada
中科院分区：
文献类型：
--
作者：
Yasutake Takahashi;M. Asada
本文提出了多层强化学习的控制结构可以被分解成更小的可传输的块，因此以前学到的知识可以应用到相关的任务，在一个新遇到的情况。较低网络中的模块被组织为专家，以移动到不同类别的传感器输出区域，并使用运动命令学习较低级别的行为。同时，高级网络中的模块被组织为专家，这些专家使用低级模块学习高级行为。我们将该方法应用到一个简单的足球的情况下，在RoboCup的背景下，显示的实验结果，并提供了讨论。
This paper proposes multi-layered reinforcement learning by which the control structure can be decomposed into smaller transportable chunks and therefore previously learned knowledge can be applied to related tasks in a newly encountered situation. The modules in the lower networks are organized as experts to move into different categories of sensor output regions and to learn, lower level behaviors using motor commands. In the meantime, the modules in the higher networks are organized as experts which learn higher level behavior using lower modules. We apply the method to a simple soccer situation in the context of RoboCup, show the experimental results, and provide a discussion.