复杂性的渐进代价

arXiv - ECON - Theoretical Economics Pub Date : 2024-08-27 DOI:arxiv-2408.14949

Martin W Cripps

{"title":"复杂性的渐进代价","authors":"Martin W Cripps","doi":"arxiv-2408.14949","DOIUrl":null,"url":null,"abstract":"We propose a measure of learning efficiency for non-finite state spaces. We\ncharacterize the complexity of a learning problem by the metric entropy of its\nstate space. We then describe how learning efficiency is determined by this\nmeasure of complexity. This is, then, applied to two models where agents learn\nhigh-dimensional states.","PeriodicalId":501188,"journal":{"name":"arXiv - ECON - Theoretical Economics","volume":"31 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The Asymptotic Cost of Complexity\",\"authors\":\"Martin W Cripps\",\"doi\":\"arxiv-2408.14949\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a measure of learning efficiency for non-finite state spaces. We\\ncharacterize the complexity of a learning problem by the metric entropy of its\\nstate space. We then describe how learning efficiency is determined by this\\nmeasure of complexity. This is, then, applied to two models where agents learn\\nhigh-dimensional states.\",\"PeriodicalId\":501188,\"journal\":{\"name\":\"arXiv - ECON - Theoretical Economics\",\"volume\":\"31 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - ECON - Theoretical Economics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.14949\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - Theoretical Economics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.14949","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

我们提出了一种衡量非无限状态空间学习效率的方法。我们用状态空间的度量熵来描述学习问题的复杂性。然后，我们描述了学习效率是如何由这种复杂性度量决定的。然后，我们将这一方法应用于两个代理学习高维状态的模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The Asymptotic Cost of Complexity

We propose a measure of learning efficiency for non-finite state spaces. We characterize the complexity of a learning problem by the metric entropy of its state space. We then describe how learning efficiency is determined by this measure of complexity. This is, then, applied to two models where agents learn high-dimensional states.

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

arXiv - ECON - Theoretical Economics

自引率

0.00%

发文量