Dependable Reinforcement Learning via Timed Differential Dynamic Logic

Runhao Wang, Yuhong Zhang, Haiying Sun, Jing Liu
{"title":"Dependable Reinforcement Learning via Timed Differential Dynamic Logic","authors":"Runhao Wang, Yuhong Zhang, Haiying Sun, Jing Liu","doi":"10.1109/ISCC53001.2021.9631442","DOIUrl":null,"url":null,"abstract":"Reinforcement learning algorithms discover policies that are lauded for their high efficiency, but don't necessarily guarantee safety. We introduce a new approach that provides the best of both worlds: learning optimal policies while enforcing the system to comply with certain model to keep the learning dependable. To this end, we propose Timed Differential Dynamic Logic to express the system properties. Our main insight is to convert the properties to runtime monitors, and use them to monitor whether the system is correctly modeled. We choose the optimal polices only if the reality matches the model, or we will abandon efficiency and instead to choose a policy that guides the agent to a modeled portion of the state space. We also propose Dependable Mixed Control (DMC) algorithm to implement a framework for application. Finally, the effectiveness of our approach is validated through a case study on Communication-Based Autonomous Control (CBAC).","PeriodicalId":270786,"journal":{"name":"2021 IEEE Symposium on Computers and Communications (ISCC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Symposium on Computers and Communications (ISCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCC53001.2021.9631442","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Reinforcement learning algorithms discover policies that are lauded for their high efficiency, but don't necessarily guarantee safety. We introduce a new approach that provides the best of both worlds: learning optimal policies while enforcing the system to comply with certain model to keep the learning dependable. To this end, we propose Timed Differential Dynamic Logic to express the system properties. Our main insight is to convert the properties to runtime monitors, and use them to monitor whether the system is correctly modeled. We choose the optimal polices only if the reality matches the model, or we will abandon efficiency and instead to choose a policy that guides the agent to a modeled portion of the state space. We also propose Dependable Mixed Control (DMC) algorithm to implement a framework for application. Finally, the effectiveness of our approach is validated through a case study on Communication-Based Autonomous Control (CBAC).
基于时间差分动态逻辑的可靠强化学习
强化学习算法发现了因效率高而受到称赞的策略,但不一定能保证安全。我们引入了一种两全其美的新方法:在学习最优策略的同时强制系统遵守特定的模型,以保持学习的可靠性。为此,我们提出了时间差分动态逻辑来表达系统的性质。我们的主要见解是将属性转换为运行时监视器,并使用它们来监视系统是否正确建模。只有当现实与模型相匹配时,我们才会选择最优策略,否则我们将放弃效率,转而选择一种策略,将智能体引导到状态空间的建模部分。我们还提出了可靠混合控制(DMC)算法来实现应用框架。最后,通过基于通信的自主控制(CBAC)的案例研究验证了该方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信