Can We Replicate Real Human Behaviour Using Artificial Neural Networks?

TL;DR

This paper explores using a human-values-based framework combined with machine learning to simulate human behavior in agent-based models, achieving good experimental agreement and outperforming reinforcement learning.

Contribution

Introduces a generic framework incorporating human values into agent-based modeling, improving simulation accuracy and versatility over traditional reinforcement learning methods.

Findings

Good agreement between simulation and experimental results.

Framework outperforms strict reinforcement learning.

Method is adaptable to various systems.

Abstract

Agent-based modelling is a powerful tool when simulating human systems, yet when human behaviour cannot be described by simple rules or maximising one's own profit, we quickly reach the limits of this methodology. Machine learning has the potential to bridge this gap by providing a link between what people observe and how they act in order to reach their goal. In this paper we use a framework for agent-based modelling that utilizes human values like fairness, conformity and altruism. Using this framework we simulate a public goods game and compare to experimental results. We can report good agreement between simulation and experiment and furthermore find that the presented framework outperforms strict reinforcement learning. Both the framework and the utility function are generic enough that they can be used for arbitrary systems, which makes this method a promising candidate for a foundation of a universal agent-based model.