Government Intervention in Catastrophe Insurance Markets: A Reinforcement Learning Approach
This work addresses the problem of policy evaluation in economics for governments and insurers, but it is incremental as it applies existing reinforcement learning methods to a new domain.
The paper tackles the problem of evaluating government policy interventions in catastrophe insurance markets by designing a sequential repeated game with individuals, insurers, and a government, using reinforcement learning to learn the welfare impact per dollar spent on proposed policies. It provides a framework for algorithmic policy evaluation based on calibrated theoretical models to assist in feasibility studies.
This paper designs a sequential repeated game of a micro-founded society with three types of agents: individuals, insurers, and a government. Nascent to economics literature, we use Reinforcement Learning (RL), closely related to multi-armed bandit problems, to learn the welfare impact of a set of proposed policy interventions per $1 spent on them. The paper rigorously discusses the desirability of the proposed interventions by comparing them against each other on a case-by-case basis. The paper provides a framework for algorithmic policy evaluation using calibrated theoretical models which can assist in feasibility studies.