Evolution for modeling

Junges, Robert; Klügl, Franziska

doi:10.1145/2001858.2002047

Cited by 9 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several other studies apply similar structural calibration techniques to various domains, such as opinion dynamics (Husselmann 2015), archaeological simulations (Gunaratne & Garibay 2017), and human crowding models (Junges & Klügl 2011;Zhong et al 2017). In Zhong et al (2017), the authors employ a "dual-layer" architecture consisting of a lower-level social force model for collision avoidance and a higher-level navigation model.…”

Section: 3mentioning

confidence: 99%

Learning Interpretable Logic for Agent-Based Models from Domain Independent Primitives

Greig

Major

Pacholska³

et al. 2023

JASSS

View full text Add to dashboard Cite

Genetic programming (GP) is a powerful method applicable to Inverse Generative Social Science (IGSS) for learning non-trivial agent logic in agent-based models (ABMs). While previous attempts at using evolutionary algorithms for learning ABM structures have focused on recombining domain-specific primitives, this paper extends prior work by developing techniques to evolve interpretable agent logic from scratch using a highly flexible domain-specific language (DSL) comprised of domain-independent primitives, such as basic mathematical operators. We demonstrate the flexibility of our method by learning symbolic models in two distinct domains: flocking and opinion dynamics, targeting data generated by reference models. Our results show that the evolved solutions closely resemble the reference models in behavior, generalize exceptionally well, and exhibit robustness to noise. Additionally, we provide an in-depth analysis of the generated code and intermediate behaviors, revealing the training process's progression. We explore techniques for further enhancing the interpretability of the resulting code and include a population-level analysis of the diversity for both models. This research demonstrates the potential of GP in IGSS for learning interpretable agent logic in ABMs across various domains.

show abstract

Section: 3mentioning

confidence: 99%

Learning Interpretable Logic for Agent-Based Models from Domain Independent Primitives

Greig

Major

Pacholska³

et al. 2023

JASSS

View full text Add to dashboard Cite

show abstract

“…Whilst the application is most emphatically not inverse generative social science, the evolutionary computing methods used in these studies, again focusing on agent decision-making processes, are very relevant to the generic requirement for model discovery. Junges & Klügl used genetic programming to find decision tree representations of agent decision-making that minimized collisions in a pedestrian evacuation scenario [13]. van Berkel and colleagues developed infrastructure for automatic discovery of behavioral algorithms for MAS, in which grammatical evolution was used to find optimal algorithm structures for solving five types of multi-agent problem, based on defined primitives implemented in the NetLogo ABM software [25].…”

Section: Related Workmentioning

confidence: 99%

Toward inverse generative social science using multi-objective genetic programming

Probst

Epstein

et al. 2019

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

Generative mechanism-based models of social systems, such as those represented by agent-based simulations, require that intraagent equations (or rules) be specified. However there are often many different choices available for specifying these equations, which can still be interpreted as falling within a particular class of mechanisms. Whilst it is important for a generative model to reproduce historically observed dynamics, it is also important for the model to be theoretically enlightening. Genetic programs (our own included) often produce concatenations that are highly predictive but are complex and hard to interpret theoretically. Here, we develop a new method -based on multi-objective genetic programming -for automating the exploration of both objectives simultaneously. We demonstrate the method by evolving the equations for an existing agent-based simulation of alcohol use behaviors based on social norms theory, the initial model structure for which was developed by a team of human modelers. We discover a trade-off between empirical fit and theoretical interpretability that offers insight into the social norms processes that influence the change and stasis in alcohol use behaviors over time.

show abstract

“…during a simulation run. Simulation data could be used to train the ML as in (Caudell et al 2011;Junges and Klügl 2011;Laite et al 2016;Yuksel 2018). The process of training an algorithm also depends on other aspects in addition to the availability of data: the nature of the problem and the algorithm itself (Tables 2-4 and Figure 2-7).…”

Section: Data For Training ML Algorithmsmentioning

confidence: 99%

Enhancing agent-based models with artificial intelligence for complex decision making

Abdulkareem¹

View full text Add to dashboard Cite

Every morning we open our eyes, check our phones, browse the social networking sites and read the unfortunate news of many disasters around the world. These disasters vary in their causes, but they are consistent with the results: losses of money and lives. Epidemics are one of these disasters that take hundreds of lives every day throughout the Globe. The spread of infectious diseases does not differentiate between humans in any part of the world they inhabit. What limits their spread is the procedures taken by governments to control them and save the lives of thousands, especially children and elders. Therefore, in order for governments to formulate correct policies in the area of health and prevention, scientific and technical tools such as agent-based models must be available. These simulation models help policymakers to study and analyse past epidemics and their patterns of diffusion, apply different scenarios and prepare for any future emergencies.

show abstract

Evolution for modeling

Cited by 9 publications

References 21 publications

Learning Interpretable Logic for Agent-Based Models from Domain Independent Primitives

Learning Interpretable Logic for Agent-Based Models from Domain Independent Primitives

Toward inverse generative social science using multi-objective genetic programming

Enhancing agent-based models with artificial intelligence for complex decision making

Contact Info

Product

Resources

About