文章基本信息

标题：Multiple Action Sequence Learning and Automatic Generation for a Humanoid Robot Using RNNPB and Reinforcement Learning
本地全文：下载
作者：Takashi Kuremoto ; Koichi Hashiguchi ; Keita Morisaki 等
期刊名称：Journal of Software Engineering and Applications
印刷版ISSN：1945-3116
电子版ISSN：1945-3124
出版年度：2012
卷号：5
期号：12B
页码：128-133
DOI：10.4236/jsea.2012.512B025
出版社：Scientific Research Publishing
摘要：This paper proposes how to learn and generate multiple action sequences of a humanoid robot. At first, all the basic action sequences, also called primitive behaviors, are learned by a recurrent neural network with parametric bias (RNNPB) and the value of the internal nodes which are parametric bias (PB) determining the output with different primitive behaviors are obtained. The training of the RNN uses back propagation through time (BPTT) method. After that, to generate the learned behaviors, or a more complex behavior which is the combination of the primitive behaviors, a reinforcement learning algorithm: Q-learning (QL) is adopt to determine which PB value is adaptive for the generation. Finally, using a real humanoid robot, the proposed method was confirmed its effectiveness by the results of experiment.
关键词：RNNPB; Humanoid robot; BPTT; reinforcement learning; multiple action sequences