Learning Discrete-Time Major-Minor Mean Field Games
Preprint
Abstract
Recent techniques based on Mean Field Games (MFGs) allow the scalable analysis of multi-player games with many similar, rational agents. However, standard MFGs remain limited to homogeneous players that weakly influence each other, and cannot model major players that strongly influence other players, severely limiting the class of problems that can be handled. We propose a novel discrete time version of major-minor MFGs (M3FGs), along with a learning algorithm based on fictitious play and partitioning the probability simplex. Importantly, M3FGs generalize MFGs with common noise and can handle not only random exogeneous environment states but also major players. A key challenge is that the mean field is stochastic and not deterministic as in standard MFGs. Our theoretical investigation verifies both the M3FG model and its algorithmic solution, showing firstly the well-posedness of the M3FG model starting from a finite game of interest, and secondly convergence and approximation guarantees of the fictitious play algorithm. Then, we empirically verify the obtained theoretical results, ablating some of the theoretical assumptions made, and show successful equilibrium learning in three example problems. Overall, we establish a learning framework for a novel and broad class of tractable games.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Master Equation for Discrete-Time Stackelberg Mean Field Games with a Single Leader2022
- Mean Field Models to Regulate Carbon Emissions in Electricity ProductionDynamic Games and Applications, 2022
- Applications of Mean Field Games in financial engineering and economic theory2021
- Array programming with NumPyNature, 2020
- Remarks on Nash equilibria in mean field game models with a major playerProceedings of the American Mathematical Society, 2020
- An Alternative Approach to Mean Field Game with Major and Minor Players, and Applications to Herders ImpactsApplied Mathematics & Optimization, 2017
- Mean Field Games with a Dominating PlayerApplied Mathematics & Optimization, 2015
- Dynamic Optimization of Large-Population Systems with Partial InformationJournal of Optimization Theory and Applications, 2015
- Large-Population LQG Games Involving a Major Player: The Nash Certainty Equivalence PrincipleSIAM Journal on Control and Optimization, 2010
- The Complexity of Computing a Nash EquilibriumSIAM Journal on Computing, 2009