This model was developed to test the usability of evolutionary computing and reinforcement learning by extending a well known agent-based model. Sugarscape (Epstein & Axtell, 1996) has been used to demonstrate migration, trade, wealth inequality, disease processes, sex, culture, and conflict. It is on conflict that this model is focused to demonstrate how machine learning methodologies could be applied.

The code is based on the Sugarscape 2 Constant Growback model, availble in the NetLogo models library. New code was added into the existing model while removing code that was not needed and modifying existing code to support the changes. Support for the original movement rule was retained while evolutionary computing, Q-Learning, and SARSA Learning were added.

The purpose of the model is to collect information on human decision-making in the context of coalition formation games. The model uses a human-in-the-loop approach, and a single human is involved in each trial. All other agents are controlled by the ABMSCORE algorithm (Vernon-Bido and Collins 2020), which is an extension of the algorithm created by Collins and Frydenlund (2018). The glove game, a standard cooperative game, is used as the model scenario.

The intent of the game is to collection information on the human players behavior and how that compares to the computerized agents behavior. The final coalition structure of the game is compared to an ideal output (the core of the games).

This model allows simulating the impacts of floods on a population. Floods are described by their intensity (flood height) and date of occurrence. Households are more or less severely hit by floods according to their geographical situation. Impacts are measured in terms of reductions in household wealth. Households may take up protection measures against floods, depending on their individual characteristics, a social network and information campaigns. If such measures are taken, flood impacts (wealth reduction) are less severe. Information campaigns increase the probability that households adopt protection measures. Two types of information campaigns are modeled: top-down policies which are the same for all households, people-centered policies, which adapt to the individual characteristics of each household.

This model is designed to show the effects of personality types and student organizations have on ones chance to making friendships in a university setting. As known from psychology studies, those that are extroverted have an easier chance making friendships in comparison to those that are introverted.
Once every tick a pair of students (nodes) will be randomly selected they will then have the chance to either be come friends or not (create an edge or not) based on their personality type (you are able to change what the effect of each personality is) and whether or not they are in the same club (you can change this value) then the model triggers the next tick cycle to begin.

This model is developed as a theoretical agent-based model to study the general phenomena of network-based targeting strategies on eco-innovation adoption and diffusion through inter-firm networks.

The purpose of this model is to examine equity and efficiency in crop production across a system of irrigated farms, as a function of maintenance costs, assessed water fees, and the capacity of farmers to trade water rights among themselves.

The model explores the impact of journal metrics (e.g., the notorious impact factor) on the perception that academics have of an article’s scientific value.

Exploring how learning and social-ecological networks influence management choice set and their ability to increase the likelihood of species coexistence (i.e. biodiversity) on a fragmented landscape controlled by different managers.

An agent-based model of urban travel behaviour in Dublin, Ireland, built in NetLogo and empirically grounded in 2016 travel survey data. Each agent represents a Dublin resident initialised with real socio-demographic attributes — including age, gender, household size and car ownership, income, driving licence status, and access to local amenities — alongside observed trip characteristics such as distance, travel time, and trip type (work, shopping, leisure).
At each time step, agents choose between four transport modes (car, public transport, cycling, and walking) across short, medium, and long trips. Mode choice is governed by a preference vector that weighs personal need satisfaction against social influence from neighbouring agents reflecting consumat framework. Satisfaction evolves dynamically based on cost (incorporating Irish motor tax bands and per-km operating rates), travel time, and trip-type suitability, with an uncertainty parameter capturing variability in perceived utility over time.
The model tracks aggregate modal shares and total CO2 emission at each tick, enabling exploration of how policy interventions — such as fuel taxation, public transport pricing, or active travel incentives — might shift the city’s travel demand profile over 100 simulated days.

Comparing impact of alternative behavioral theories in a simple social-ecological system.