arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10643cs.LGcs.SYeess.SY
收藏

基于鲁棒动作调节器的安全强化学习

Safe Reinforcement Learning Using Robust Action Governor

University of Michigan(密歇根大学);Ford Motor Company(福特汽车公司)

Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky

摘要:

强化学习(RL)本质上是一种试错学习过程,在探索和利用过程中可能会导致不安全的行为。这阻碍了RL在现实世界控制问题中的应用,特别是对安全关键系统的应用。在本文中,我们介绍了一个安全RL的框架,该框架基于RL算法与附加安全监督模块的集成,称为鲁棒动作总督(RAG),该模块利用集合理论技术和在线优化来管理学习过程中的安全相关要求。我们说明了这一建议的安全RL框架,通过应用汽车自适应巡航控制。

英文摘要:

Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially to those for safety-critical systems. In this paper, we introduce a framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning. We illustrate this proposed safe RL framework through an application to automotive adaptive cruise control.

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。

↑