文章基本信息

标题：Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks
本地全文：下载
作者：Haonan Chang ; Zhuo Xu ; Masayoshi Tomizuka 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2020
卷号：53
期号：2
页码：8181-8186
DOI：10.1016/j.ifacol.2020.12.2317
语种：English
出版社：Elsevier
摘要：AbstractReinforcement learning methods have been developed to achieve great success in training control policies in various automation tasks. However, a main challenge of the wider application of reinforcement learning in practical automation is that the training process is hard and the pretrained policy networks are hardly reusable in other similar cases. To address this problem, we propose the cascade attribute network (CAN), which utilizes its hierarchical structure to decompose a complicated control policy in terms of the requirement constraints, which we call attributes, encoded in the control tasks. We validated the effectiveness of our proposed method on two robot control scenarios with various add-on attributes. For some control tasks with more than one add-on attribute attribute, by directly assembling the attribute modules in cascade, the CAN can provide ideal control policies in a zero-shot manner.
关键词：KeywordsReinforcement learning controlDeep LearningArtificial Intelligence