Abstract
Machine learning (ML) algorithms steer agent decisions in agent-based models (ABMs), serving as a vehicle for implementing behaviour changes during simulation runs. However, when training an ML algorithm, obtaining large sets of micro-level human behaviour data is often problematic. Information on human behaviour is often collected via surveys of relatively small sample sizes. This paper presents a methodology for training a learning algorithm to guide agent behaviour in a spatial ABM using a limited survey data sample. We apply different implementation strategies using survey data and Bayesian networks (BNs). By being grounded in probabilistic directed graphical models, BNs stand out among other learning algorithms in that they can be based on expert knowledge and/or known datasets. This paper presents four alternative implementations of data-driven BNs to support agent decisions in a spatial ABM. We differentiate between training BNs prior to, or during the simulation runs, using only survey data or a combination of survey data and expert knowledge. The four different implementations are then illustrated using a spatial ABM of cholera diffusion for Kumasi, Ghana. The results indicate that a balance between expert knowledge and survey data provides the best control over the learning process of the agents and produces the most realistic agent behaviour.
Highlights
Learning can be defined as a process in which prior knowledge gained from experience is employed to optimise future decisions [1]
EEBN has the second-best scores, confirming that the involvement of experts leads to a better fit than using data only. This holds true for both the structure of the Bayesian networks (BNs) and estimation of probabilistic parameters and conditional probability tables (CPTs) for the network, as indicated by the scores for EEBN
We evaluated the outcomes of the Cholera ABM (CABM) by dividing agents into groups according to their level of risk perception
Summary
Learning can be defined as a process in which prior knowledge gained from experience is employed to optimise future decisions [1]. The proliferation of agent-based models (ABMs) as Extended author information available on the last page of the article. GeoInformatica (2019) 23:243–268 a research method calls for advancements in how agents learn and adapt. In ABMs, agents can possess their own cognitive model that can be trained using real data. Machine learning (ML) algorithms are used increasingly to enhance agent learning abilities and implement autonomous smart behaviour. ABMs with intelligent agents are argued to capture complex real-world phenomena more realistically [2]. The behavioural rules guiding an individual agent’s decisions, and the interactions between agents and environments, significantly affects the macro-patterns emerging from a model [3]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
