The impact of moving expenses on social segregation: a simulation with RL and ABM
This work addresses social segregation for policymakers by providing a simulation tool, but it is incremental as it combines existing RL and ABM methods in a modified model.
The paper tackled the problem of understanding how moving expenses affect social segregation by simulating a modified Schelling Segregation model using Reinforcement Learning (RL) and Agent-based modeling (ABM), with results showing insights into segregation patterns and social integration for policy forecasting.
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.