An, L, Grimm, V, Bai, Y et al. (9 more authors) (2023) Modeling agent decision and behavior in the light of data science and artificial intelligence. Environmental Modelling and Software, 166. 105713. ISSN 1364-8152
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.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023, Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/.This is an author produced version of an article published in Environmental Modelling & Software. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Agent-based modeling, Modeling agent decisions and actions, Artificial intelligence, Machine learning, Data science |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Environment (Leeds) > School of Geography (Leeds) > Centre for Spatial Analysis & Policy (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 06 Jul 2023 16:17 |
Last Modified: | 06 Jul 2023 16:17 |
Status: | Published |
Publisher: | Elsevier |
Identification Number: | 10.1016/j.envsoft.2023.105713 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:200034 |