一种基于策略迭代算法的逆方法

Infinity Pub Date : 2009-11-17 DOI:10.4204/EPTCS.10.4
L. Fribourg, É. André
{"title":"一种基于策略迭代算法的逆方法","authors":"L. Fribourg, É. André","doi":"10.4204/EPTCS.10.4","DOIUrl":null,"url":null,"abstract":"We present an extension of two policy-iteration based algorithms on weighted graphs (viz., Markov Decision Problems and Max-Plus Algebras). This extension allows us to solve the following inverse problem: considering the weights of the graph to be unknown constants or parameters, we suppose that a reference instantiation of those weights is given, and we aim at computing a constraint on the parameters under which an optimal policy for the reference instantiation is still optimal. The original algorithm is thus guaranteed to behave well around the reference instantiation, which provides us with some criteria of robustness. We present an application of both methods to simple examples. A prototype implementation has been done.","PeriodicalId":31175,"journal":{"name":"Infinity","volume":"11 22 1","pages":"44-61"},"PeriodicalIF":0.0000,"publicationDate":"2009-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"An Inverse Method for Policy-Iteration Based Algorithms\",\"authors\":\"L. Fribourg, É. André\",\"doi\":\"10.4204/EPTCS.10.4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present an extension of two policy-iteration based algorithms on weighted graphs (viz., Markov Decision Problems and Max-Plus Algebras). This extension allows us to solve the following inverse problem: considering the weights of the graph to be unknown constants or parameters, we suppose that a reference instantiation of those weights is given, and we aim at computing a constraint on the parameters under which an optimal policy for the reference instantiation is still optimal. The original algorithm is thus guaranteed to behave well around the reference instantiation, which provides us with some criteria of robustness. We present an application of both methods to simple examples. A prototype implementation has been done.\",\"PeriodicalId\":31175,\"journal\":{\"name\":\"Infinity\",\"volume\":\"11 22 1\",\"pages\":\"44-61\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-11-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Infinity\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4204/EPTCS.10.4\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Infinity","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4204/EPTCS.10.4","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

我们提出了两种基于策略迭代的加权图算法(即马尔可夫决策问题和Max-Plus代数)的扩展。这个扩展允许我们解决以下反问题:考虑到图的权重是未知的常量或参数,我们假设这些权重的参考实例化是给定的,我们的目标是计算一个参数约束,在这个参数约束下,参考实例化的最优策略仍然是最优的。从而保证了原始算法在引用实例化周围的良好行为,为我们提供了一些鲁棒性准则。我们给出了两种方法在简单例子中的应用。已经完成了原型实现。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
An Inverse Method for Policy-Iteration Based Algorithms
We present an extension of two policy-iteration based algorithms on weighted graphs (viz., Markov Decision Problems and Max-Plus Algebras). This extension allows us to solve the following inverse problem: considering the weights of the graph to be unknown constants or parameters, we suppose that a reference instantiation of those weights is given, and we aim at computing a constraint on the parameters under which an optimal policy for the reference instantiation is still optimal. The original algorithm is thus guaranteed to behave well around the reference instantiation, which provides us with some criteria of robustness. We present an application of both methods to simple examples. A prototype implementation has been done.
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
2.30
自引率
0.00%
发文量
26
审稿时长
10 weeks
期刊最新文献
Sistem Informasi Perpustakaan Pada SMKN 3 Tana Toraja Dengan Metode Rapid Application Development (RAD) Perancangan Sistem Informasi Paket Wisata Berbasis Web Studi Kasus Sarira Trip Penggunaan YOLOv4 Untuk Menentukan Lokasi Dosen Dan Mahasiswa Dengan Menggunakan CCTV Aplikasi Reservasi Pantan Toraja Hotel Prediksi Persediaan Sepeda Motor Pada Dealer Yamaha Jaya Baru Motor Mengunakan Metode Frequent Pattern (FF-Growth)
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1