Modeling agent decision and behavior in the light of data science and artificial intelligence

Li An, Volker Grimm, Yu Bai, Abigail Sullivan, B. L. Turner, Nicolas Malleson, Alison Heppenstall, Christian Vincenot, Derek Robinson, Xinyue Ye, Jianguo Liu, Emilie Lindkvist, Wenwu Tang

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

Abstract

Agent-based modeling (ABM) has been widely used in numerous disciplines and practice domains, subject to many eulogies and criticisms. This article presents key advances and challenges in agent-based modeling over the last two decades and shows that understanding agents’ behaviors is a major priority for various research fields. We demonstrate that artificial intelligence and data science will likely generate revolutionary impacts for science and technology towards understanding agent decisions and behaviors in complex systems. We propose an innovative approach that leverages reinforcement learning and convolutional neural networks to equip agents with the intelligence of self-learning their behavior rules directly from data. We call for further developments of ABM, especially modeling agent behaviors, in the light of data science and artificial intelligence.

Original languageEnglish (US)
Article number105713
JournalEnvironmental Modelling and Software
Volume166
DOIs
StatePublished - Aug 2023
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Environmental Engineering
  • Ecological Modeling

Keywords

  • Agent-based modeling
  • Artificial intelligence
  • Data science
  • Machine learning
  • Modeling agent decisions and actions

Fingerprint

Dive into the research topics of 'Modeling agent decision and behavior in the light of data science and artificial intelligence'. Together they form a unique fingerprint.

Cite this