Reinforcement Learning Algorithm for Mixed Mean Field Control Games
Journal of Machine Learning · 2023
DOI: 10.4208/jml.220915 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Machine Learning, 2023. Verfasst von Andrea Angiuli und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Angiuli, A., Detering, N., Fouque, J., Laurière, M., & Lin, J. (2023). Reinforcement Learning Algorithm for Mixed Mean Field Control Games. Journal of Machine Learning. https://doi.org/10.4208/jml.220915
Vancouver
Angiuli A, Detering N, Fouque J, Laurière M, Lin J. Reinforcement Learning Algorithm for Mixed Mean Field Control Games. Journal of Machine Learning. 2023. doi:10.4208/jml.220915
BibTeX
@article{Angiuli2023,
author = {Angiuli, Andrea and Detering, Nils and Fouque, Jean-Pierre and Laurière, Mathieu and Lin, Jimin},
title = {Reinforcement Learning Algorithm for Mixed Mean Field Control Games},
journal = {Journal of Machine Learning},
year = {2023},
doi = {10.4208/jml.220915}
}
EUVIMED