基于线性函数逼近的差分私有强化学习

Xingyu Zhou
{"title":"基于线性函数逼近的差分私有强化学习","authors":"Xingyu Zhou","doi":"10.1145/3508028","DOIUrl":null,"url":null,"abstract":"Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision processes (MDPs) under the constraints of differential privacy (DP). Compared to existing private RL algorithms that work only on tabular finite-state, finite-actions MDPs, we take the first step towards privacy-preserving learning in MDPs with large state and action spaces. Specifically, we consider MDPs with linear function approximation (in particular linear mixture MDPs) under the notion of joint differential privacy (JDP), where the RL agent is responsible for protecting users' sensitive data. We design two private RL algorithms that are based on value iteration and policy optimization, respectively, and show that they enjoy sub-linear regret performance while guaranteeing privacy protection. Moreover, the regret bounds are independent of the number of states, and scale at most logarithmically with the number of actions, making the algorithms suitable for privacy protection in nowadays large-scale personalized services. Our results are achieved via a general procedure for learning in linear mixture MDPs under changing regularizers, which not only generalizes previous results for non-private learning, but also serves as a building block for general private reinforcement learning.","PeriodicalId":426760,"journal":{"name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","volume":"90 9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":"{\"title\":\"Differentially Private Reinforcement Learning with Linear Function Approximation\",\"authors\":\"Xingyu Zhou\",\"doi\":\"10.1145/3508028\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision processes (MDPs) under the constraints of differential privacy (DP). Compared to existing private RL algorithms that work only on tabular finite-state, finite-actions MDPs, we take the first step towards privacy-preserving learning in MDPs with large state and action spaces. Specifically, we consider MDPs with linear function approximation (in particular linear mixture MDPs) under the notion of joint differential privacy (JDP), where the RL agent is responsible for protecting users' sensitive data. We design two private RL algorithms that are based on value iteration and policy optimization, respectively, and show that they enjoy sub-linear regret performance while guaranteeing privacy protection. Moreover, the regret bounds are independent of the number of states, and scale at most logarithmically with the number of actions, making the algorithms suitable for privacy protection in nowadays large-scale personalized services. Our results are achieved via a general procedure for learning in linear mixture MDPs under changing regularizers, which not only generalizes previous results for non-private learning, but also serves as a building block for general private reinforcement learning.\",\"PeriodicalId\":426760,\"journal\":{\"name\":\"Proceedings of the ACM on Measurement and Analysis of Computing Systems\",\"volume\":\"90 9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"14\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ACM on Measurement and Analysis of Computing Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3508028\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3508028","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 14

摘要

由于强化学习(RL)在现实世界个性化服务中的广泛应用,用户的敏感和隐私信息需要得到保护,我们研究了差分隐私(DP)约束下有限视界马尔可夫决策过程(mdp)中的遗憾最小化。与现有的仅适用于表格有限状态、有限动作mdp的私有强化学习算法相比,我们在具有大状态和动作空间的mdp中迈出了保护隐私学习的第一步。具体来说,我们在联合差分隐私(JDP)的概念下考虑线性函数近似的mdp(特别是线性混合mdp),其中RL代理负责保护用户的敏感数据。我们设计了两种分别基于值迭代和策略优化的私有RL算法,并证明它们在保证隐私保护的同时具有亚线性后悔性能。此外,遗憾边界与状态数无关,且最多与动作数成对数比例,使得算法适用于当今大规模个性化服务中的隐私保护。我们的结果是通过在变化正则器下的线性混合mdp中学习的一般过程获得的,这不仅推广了以前的非私有学习结果,而且还作为一般私有强化学习的构建块。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Differentially Private Reinforcement Learning with Linear Function Approximation
Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in finite-horizon Markov decision processes (MDPs) under the constraints of differential privacy (DP). Compared to existing private RL algorithms that work only on tabular finite-state, finite-actions MDPs, we take the first step towards privacy-preserving learning in MDPs with large state and action spaces. Specifically, we consider MDPs with linear function approximation (in particular linear mixture MDPs) under the notion of joint differential privacy (JDP), where the RL agent is responsible for protecting users' sensitive data. We design two private RL algorithms that are based on value iteration and policy optimization, respectively, and show that they enjoy sub-linear regret performance while guaranteeing privacy protection. Moreover, the regret bounds are independent of the number of states, and scale at most logarithmically with the number of actions, making the algorithms suitable for privacy protection in nowadays large-scale personalized services. Our results are achieved via a general procedure for learning in linear mixture MDPs under changing regularizers, which not only generalizes previous results for non-private learning, but also serves as a building block for general private reinforcement learning.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
3.20
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:481959085
Book学术官方微信