Parameterizing agent-based models using an online game

IF 7.1 1区地球科学 Q1 ENVIRONMENTAL STUDIES

Computers Environment and Urban Systems Pub Date : 2024-06-20 DOI:10.1016/j.compenvurbsys.2024.102142

Niko Yiannakoulias , Michel Grignon , Tara Marshall

{"title":"Parameterizing agent-based models using an online game","authors":"Niko Yiannakoulias , Michel Grignon , Tara Marshall","doi":"10.1016/j.compenvurbsys.2024.102142","DOIUrl":null,"url":null,"abstract":"<div><p>Agent-based models (ABMs) of human systems are often parameterized using real-world data. For some ABMs this is not possible because the reality upon which the models are based does not exist or is not generalizable from one setting to another. In this paper we implement an online decision game to parameterize an agent-based model of pedestrian and cyclist route choice decisions in a neighbourhood. Our conceptual framework is to use an experimental game to log decision-making behaviour, summarize this behaviour into a decision model, and then transfer this model to an ABM. The product of this framework is an ABM with agents informed by human decision making made within the game, rather than the real world. The results of our analysis suggest that the decision model is consistent with some general theory about decision making, but the ABM illustrates some unique and contextually specific patterns of flow. ABMs parameterized with game data may be useful for forecasting the effects of change on urban transportation infrastructure.</p></div>","PeriodicalId":48241,"journal":{"name":"Computers Environment and Urban Systems","volume":"112 ","pages":"Article 102142"},"PeriodicalIF":7.1000,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0198971524000711/pdfft?md5=c53083a997f0477049542e9312bd474e&pid=1-s2.0-S0198971524000711-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers Environment and Urban Systems","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0198971524000711","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}

引用次数: 0

Abstract

Agent-based models (ABMs) of human systems are often parameterized using real-world data. For some ABMs this is not possible because the reality upon which the models are based does not exist or is not generalizable from one setting to another. In this paper we implement an online decision game to parameterize an agent-based model of pedestrian and cyclist route choice decisions in a neighbourhood. Our conceptual framework is to use an experimental game to log decision-making behaviour, summarize this behaviour into a decision model, and then transfer this model to an ABM. The product of this framework is an ABM with agents informed by human decision making made within the game, rather than the real world. The results of our analysis suggest that the decision model is consistent with some general theory about decision making, but the ABM illustrates some unique and contextually specific patterns of flow. ABMs parameterized with game data may be useful for forecasting the effects of change on urban transportation infrastructure.

查看原文本刊更多论文

利用在线游戏为基于代理的模型设定参数

基于代理的人类系统模型（ABM）通常使用真实世界的数据进行参数化。对于某些 ABM 而言，这是不可能的，因为模型所基于的现实并不存在，或者无法从一个环境推广到另一个环境。在本文中，我们实施了一个在线决策游戏，对基于代理的邻里行人和骑自行车者路线选择决策模型进行参数化。我们的概念框架是利用实验游戏记录决策行为，将这些行为总结为决策模型，然后将该模型转移到人工智能模型中。这一框架的产物是一个人工智能模型，其代理信息来自游戏中的人类决策，而非现实世界。我们的分析结果表明，决策模型与一些关于决策的一般理论是一致的，但人工智能模型展示了一些独特的、与具体情况相关的流程模式。以游戏数据为参数的 ABM 可能有助于预测变化对城市交通基础设施的影响。

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

Computers Environment and Urban Systems Multiple-

CiteScore

13.30

自引率

7.40%

发文量

111

审稿时长

32 days

期刊介绍： Computers, Environment and Urban Systemsis an interdisciplinary journal publishing cutting-edge and innovative computer-based research on environmental and urban systems, that privileges the geospatial perspective. The journal welcomes original high quality scholarship of a theoretical, applied or technological nature, and provides a stimulating presentation of perspectives, research developments, overviews of important new technologies and uses of major computational, information-based, and visualization innovations. Applied and theoretical contributions demonstrate the scope of computer-based analysis fostering a better understanding of environmental and urban systems, their spatial scope and their dynamics.