因果发现的元强化学习算法

CLEaR Pub Date : 2022-07-18 DOI:10.48550/arXiv.2207.08457
A. Sauter, Erman Acar, Vincent François-Lavet
{"title":"因果发现的元强化学习算法","authors":"A. Sauter, Erman Acar, Vincent François-Lavet","doi":"10.48550/arXiv.2207.08457","DOIUrl":null,"url":null,"abstract":"Causal discovery is a major task with the utmost importance for machine learning since causal structures can enable models to go beyond pure correlation-based inference and significantly boost their performance. However, finding causal structures from data poses a significant challenge both in computational effort and accuracy, let alone its impossibility without interventions in general. In this paper, we develop a meta-reinforcement learning algorithm that performs causal discovery by learning to perform interventions such that it can construct an explicit causal graph. Apart from being useful for possible downstream applications, the estimated causal graph also provides an explanation for the data-generating process. In this article, we show that our algorithm estimates a good graph compared to the SOTA approaches, even in environments whose underlying causal structure is previously unseen. Further, we make an ablation study that shows how learning interventions contribute to the overall performance of our approach. We conclude that interventions indeed help boost the performance, efficiently yielding an accurate estimate of the causal structure of a possibly unseen environment.","PeriodicalId":171742,"journal":{"name":"CLEaR","volume":"62 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"A Meta-Reinforcement Learning Algorithm for Causal Discovery\",\"authors\":\"A. Sauter, Erman Acar, Vincent François-Lavet\",\"doi\":\"10.48550/arXiv.2207.08457\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Causal discovery is a major task with the utmost importance for machine learning since causal structures can enable models to go beyond pure correlation-based inference and significantly boost their performance. However, finding causal structures from data poses a significant challenge both in computational effort and accuracy, let alone its impossibility without interventions in general. In this paper, we develop a meta-reinforcement learning algorithm that performs causal discovery by learning to perform interventions such that it can construct an explicit causal graph. Apart from being useful for possible downstream applications, the estimated causal graph also provides an explanation for the data-generating process. In this article, we show that our algorithm estimates a good graph compared to the SOTA approaches, even in environments whose underlying causal structure is previously unseen. Further, we make an ablation study that shows how learning interventions contribute to the overall performance of our approach. We conclude that interventions indeed help boost the performance, efficiently yielding an accurate estimate of the causal structure of a possibly unseen environment.\",\"PeriodicalId\":171742,\"journal\":{\"name\":\"CLEaR\",\"volume\":\"62 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"CLEaR\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2207.08457\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"CLEaR","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2207.08457","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

因果发现是机器学习中最重要的一项主要任务,因为因果结构可以使模型超越纯粹的基于相关性的推理,并显着提高其性能。然而,从数据中寻找因果结构在计算工作量和准确性方面都提出了重大挑战,更不用说没有一般干预就不可能了。在本文中,我们开发了一种元强化学习算法,该算法通过学习执行干预来执行因果发现,从而可以构建显式因果图。除了对可能的下游应用程序有用之外,估计的因果图还为数据生成过程提供了解释。在本文中,我们展示了与SOTA方法相比,我们的算法估计了一个很好的图,即使在以前看不见潜在因果结构的环境中也是如此。此外,我们进行了一项消融研究,显示了学习干预如何有助于我们方法的整体表现。我们的结论是,干预确实有助于提高表现,有效地产生对可能看不见的环境的因果结构的准确估计。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Meta-Reinforcement Learning Algorithm for Causal Discovery
Causal discovery is a major task with the utmost importance for machine learning since causal structures can enable models to go beyond pure correlation-based inference and significantly boost their performance. However, finding causal structures from data poses a significant challenge both in computational effort and accuracy, let alone its impossibility without interventions in general. In this paper, we develop a meta-reinforcement learning algorithm that performs causal discovery by learning to perform interventions such that it can construct an explicit causal graph. Apart from being useful for possible downstream applications, the estimated causal graph also provides an explanation for the data-generating process. In this article, we show that our algorithm estimates a good graph compared to the SOTA approaches, even in environments whose underlying causal structure is previously unseen. Further, we make an ablation study that shows how learning interventions contribute to the overall performance of our approach. We conclude that interventions indeed help boost the performance, efficiently yielding an accurate estimate of the causal structure of a possibly unseen environment.
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
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