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.

This model implements two types of network diffusion from an initial group of activated nodes. In complex contagion, a node is activated if the proportion of neighbour nodes that are already activated exceeds a given threshold. This is intended to represented the spread of health behaviours. In simple contagion, an activated node has a given probability of activating its inactive neighbours and re-tests each time step until all of the neighbours are activated. This is intended to represent information spread.

A range of networks are included with the model from secondary school friendship networks. The proportion of nodes initially activated and the method of selecting those nodes are controlled by the user.

The HUMan impact on LANDscapes (HUMLAND) model has been developed to track and quantify the intensity of different impacts on landscapes at the continental level. This agent-based model focuses on determining the most influential factors in the transformation of interglacial vegetation with a specific emphasis on burning organized by hunter-gatherers. HUMLAND integrates various spatial datasets as input and target for the agent-based model results. Additionally, the simulation incorporates recently obtained continental-scale estimations of fire return intervals and the speed of vegetation regrowth. The obtained results include maps of possible scenarios of modified landscapes in the past and quantification of the impact of each agent, including climate, humans, megafauna, and natural fires.

This models simulate how people choose their food buyings based on a limited budget and a food quality index. In order to make the choice the agents call a genetic algorithm who optimizes the buying. The agents are distributed randomly and there are 5 store options where agents can buy meat, fruits and vegetables, bread, ultraprocessed and medications. Agents need all of them, each of one has a different price and a different quality index. The genetic algorithm perform an optimization procedure in order to clasiffy what food set is the best for each agent. The agents are coloured based on their budget if the’ve got less than 100, then they are pink otherwise they are white.

This model is to match students and schools using real-world student admission mechanisms. The mechanisms in this model are serial dictatorship, deferred acceptance, the Boston mechanism, Chinese Parallel, and the Taipei mechanism.

Agent-Based-Modeling - space colonization
ask me for the .nlogo model
WHAT IS IT?
The goal of this project is to simulate with NetLogo (v6.2) a space colonization of humans, starting from Earth, into the Milky Way.

HOW IT WORKS
…

Objective of our model is to simulate the emergence and operation of a technological niches (TN) in terms of actors’ interaction. A TN can be conceived as protected socio-economic space where radical innovations are developed and tested

Merger and acquisition (M&A) activity has many strategic and operational objectives. One operational objective is to develop common and efficient information systems that maybe the source of creating

The model integrates major theories of political judgment and behavior within the classical cognitive paradigm embedded in the ACT-R cognitive architecture. It models preferences and beliefs of political candidates, parties, and groups.

This model is a replication of that described by Peterson (2002) and illustrates the ‘spread’ feedback loop type described in Millington (2013).