Risk-sensitive reinforcement learning: a martingale approach to reward uncertainty

N. Vadori, Sumitra Ganesh, P. Reddy, M. Veloso
{"title":"Risk-sensitive reinforcement learning: a martingale approach to reward uncertainty","authors":"N. Vadori, Sumitra Ganesh, P. Reddy, M. Veloso","doi":"10.1145/3383455.3422519","DOIUrl":null,"url":null,"abstract":"We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the cumulative reward as a whole, we aim at learning policies sensitive to the uncertain/stochastic nature of the rewards, which has the advantage of being conceptually more meaningful in some cases. To this end, we present a new decomposition of the randomness contained in the cumulative reward based on the Doob decomposition of a stochastic process, and introduce a new conceptual tool - the chaotic variation - which can rigorously be interpreted as the risk measure of the martingale component associated to the cumulative reward process. We innovate on the reinforcement learning side by incorporating this new risk-sensitive approach into model-free algorithms, both policy gradient and value function based, and illustrate its relevance on grid world and portfolio optimization problems.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the First ACM International Conference on AI in Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3383455.3422519","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the cumulative reward as a whole, we aim at learning policies sensitive to the uncertain/stochastic nature of the rewards, which has the advantage of being conceptually more meaningful in some cases. To this end, we present a new decomposition of the randomness contained in the cumulative reward based on the Doob decomposition of a stochastic process, and introduce a new conceptual tool - the chaotic variation - which can rigorously be interpreted as the risk measure of the martingale component associated to the cumulative reward process. We innovate on the reinforcement learning side by incorporating this new risk-sensitive approach into model-free algorithms, both policy gradient and value function based, and illustrate its relevance on grid world and portfolio optimization problems.
风险敏感强化学习:奖励不确定性的鞅方法
我们引入了一个新的框架来解释顺序决策问题对奖励不确定性的敏感性。虽然迄今为止研究的马尔可夫决策过程的风险敏感公式集中在累积奖励的整体分布上,但我们的目标是学习对奖励的不确定性/随机性敏感的策略,这在某些情况下具有概念上更有意义的优势。为此,我们在随机过程的Doob分解的基础上提出了一种新的累积奖励随机性分解方法,并引入了一个新的概念工具——混沌变异,它可以严格地解释为与累积奖励过程相关的鞅分量的风险度量。我们在强化学习方面进行了创新,将这种新的风险敏感方法结合到无模型算法中,包括策略梯度和基于价值函数的算法,并说明了其在网格世界和投资组合优化问题上的相关性。
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:481959085
Book学术官方微信