Reinforcement Learning Algorithm for Mixed Mean Field Control Games

Year:    2023

Author:    Andrea Angiuli, Nils Detering, Jean-Pierre Fouque, Mathieu Laurière, Jimin Lin

Journal of Machine Learning, Vol. 2 (2023), Iss. 2 : pp. 108–137

Abstract

We present a new combined mean field control game (MFCG) problem which can be interpreted as a competitive game between collaborating groups and its solution as a Nash equilibrium between groups. Players coordinate their strategies within each group. An example is a modification of the classical trader’s problem. Groups of traders maximize their wealth. They face cost for their transactions, for their own terminal positions, and for the average holding within their group. The asset price is impacted by the trades of all agents. We propose a three-timescale reinforcement learning algorithm to approximate the solution of such MFCG problems. We test the algorithm on benchmark linear-quadratic specifications for which we provide analytic solutions.

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/jml.220915

Journal of Machine Learning, Vol. 2 (2023), Iss. 2 : pp. 108–137

Published online:    2023-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    30

Keywords:    Mean Field Control Games Reinforcement Learning Q-Learning Optimal Liquidation.

Author Details

Andrea Angiuli

Nils Detering

Jean-Pierre Fouque

Mathieu Laurière

Jimin Lin

  1. Optimal bailout strategies resulting from the drift controlled supercooled Stefan problem

    Cuchiero, Christa | Reisinger, Christoph | Rigger, Stefan

    Annals of Operations Research, Vol. 336 (2024), Iss. 1-2 P.1315

    https://doi.org/10.1007/s10479-023-05293-7 [Citations: 2]
  2. Markov decision processes under model uncertainty

    Neufeld, Ariel | Sester, Julian | Šikić, Mario

    Mathematical Finance, Vol. 33 (2023), Iss. 3 P.618

    https://doi.org/10.1111/mafi.12381 [Citations: 4]