The impact of moving expenses on social segregation: a simulation with RL and ABM

TL;DR

This paper combines Reinforcement Learning and Agent-Based Modeling to simulate how moving expenses influence neighborhood segregation, providing insights for policymakers on social integration effects.

Contribution

It introduces a novel integration of RL with ABM in a modified Schelling model to analyze the impact of moving costs on segregation patterns.

Findings

Moving expenses significantly affect segregation levels.

RL agents effectively simulate household decision-making.

Policy simulations can forecast social integration outcomes.

Abstract

Over the past decades, breakthroughs such as Reinforcement Learning (RL) and Agent-based modeling (ABM) have made simulations of economic models feasible. Recently, there has been increasing interest in applying ABM to study the impact of residential preferences on neighborhood segregation in the Schelling Segregation Model. In this paper, RL is combined with ABM to simulate a modified Schelling Segregation model, which incorporates moving expenses as an input parameter. In particular, deep Q network (DQN) is adopted as RL agents' learning algorithm to simulate the behaviors of households and their preferences. This paper studies the impact of moving expenses on the overall segregation pattern and its role in social integration. A more comprehensive simulation of the segregation model is built for policymakers to forecast the potential consequences of their policies.