Reinforcement Learning for Intra-and-Inter-Bank Borrowing and Lending Mean Field Control Game

TL;DR

This paper introduces a mean field control game model for intra- and inter-bank borrowing and lending, providing a reinforcement learning algorithm to learn optimal strategies in a data-driven setting, with empirical validation.

Contribution

It develops a novel mean field control game framework for banking interactions and proposes a three-timescale reinforcement learning algorithm for strategy optimization.

Findings

The three-timescale approach improves convergence.

Exploration strategies significantly impact learning when models are unknown.

Empirical results confirm the effectiveness of the proposed algorithm.

Abstract

We propose a mean field control game model for the intra-and-inter-bank borrowing and lending problem. This framework allows to study the competitive game arising between groups of collaborative banks. The solution is provided in terms of an asymptotic Nash equilibrium between the groups in the infinite horizon. A three-timescale reinforcement learning algorithm is applied to learn the optimal borrowing and lending strategy in a data driven way when the model is unknown. An empirical numerical analysis shows the importance of the three-timescale, the impact of the exploration strategy when the model is unknown, and the convergence of the algorithm.