走向理解人的机器

IF 2.5 4区计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Ai Magazine Pub Date : 2023-09-04 DOI:10.1002/aaai.12116

Andrew Howes, Jussi P. P. Jokinen, Antti Oulasvirta

{"title":"走向理解人的机器","authors":"Andrew Howes, Jussi P. P. Jokinen, Antti Oulasvirta","doi":"10.1002/aaai.12116","DOIUrl":null,"url":null,"abstract":"<p>The ability to estimate the state of a human partner is an insufficient basis on which to build cooperative agents. Also needed is an ability to predict how people adapt their behavior in response to an agent's actions. We propose a new approach based on computational rationality, which models humans based on the idea that predictions can be derived by calculating policies that are approximately optimal given human-like bounds. Computational rationality brings together reinforcement learning and cognitive modeling in pursuit of this goal, facilitating machine understanding of humans.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 3","pages":"312-327"},"PeriodicalIF":2.5000,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12116","citationCount":"1","resultStr":"{\"title\":\"Towards machines that understand people\",\"authors\":\"Andrew Howes, Jussi P. P. Jokinen, Antti Oulasvirta\",\"doi\":\"10.1002/aaai.12116\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The ability to estimate the state of a human partner is an insufficient basis on which to build cooperative agents. Also needed is an ability to predict how people adapt their behavior in response to an agent's actions. We propose a new approach based on computational rationality, which models humans based on the idea that predictions can be derived by calculating policies that are approximately optimal given human-like bounds. Computational rationality brings together reinforcement learning and cognitive modeling in pursuit of this goal, facilitating machine understanding of humans.</p>\",\"PeriodicalId\":7854,\"journal\":{\"name\":\"Ai Magazine\",\"volume\":\"44 3\",\"pages\":\"312-327\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2023-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12116\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ai Magazine\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/aaai.12116\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ai Magazine","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/aaai.12116","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 1

摘要

估计人类伴侣状态的能力不足以建立合作主体。还需要一种预测人们如何根据代理人的行为调整自己的行为的能力。我们提出了一种基于计算合理性的新方法，该方法基于这样一种思想对人类进行建模，即可以通过计算在给定类人类边界的情况下近似最优的策略来导出预测。计算理性将强化学习和认知建模结合在一起，以实现这一目标，促进机器对人类的理解。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Towards machines that understand people

查看原文本刊更多论文

Towards machines that understand people

The ability to estimate the state of a human partner is an insufficient basis on which to build cooperative agents. Also needed is an ability to predict how people adapt their behavior in response to an agent's actions. We propose a new approach based on computational rationality, which models humans based on the idea that predictions can be derived by calculating policies that are approximately optimal given human-like bounds. Computational rationality brings together reinforcement learning and cognitive modeling in pursuit of this goal, facilitating machine understanding of humans.

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

Ai Magazine 工程技术-计算机：人工智能

CiteScore

3.90

自引率

11.10%

发文量

审稿时长

>12 weeks

期刊介绍： AI Magazine publishes original articles that are reasonably self-contained and aimed at a broad spectrum of the AI community. Technical content should be kept to a minimum. In general, the magazine does not publish articles that have been published elsewhere in whole or in part. The magazine welcomes the contribution of articles on the theory and practice of AI as well as general survey articles, tutorial articles on timely topics, conference or symposia or workshop reports, and timely columns on topics of interest to AI scientists.