TY - JOUR
T1 - Reinforcement Learning Algorithm for Mixed Mean Field Control Games
AU - Angiuli , Andrea
AU - Detering , Nils
AU - Fouque , Jean-Pierre
AU - Laurière , Mathieu
AU - Lin , Jimin
JO - Journal of Machine Learning
VL - 2
SP - 108
EP - 137
PY - 2023
DA - 2023/06
SN - 2
DO - http://doi.org/10.4208/jml.220915
UR - https://global-sci.org/intro/article_detail/jml/21757.html
KW - Mean Field Control Games, Reinforcement Learning, Q-Learning, Optimal Liquidation.
AB - <p style="text-align: justify;">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.</p>