Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games

Multi-population mean-field game is a critical subclass of mean-field games (MFGs). It is a theoretically feasible multi-agent model for simulating and analyzing the game between multiple heterogeneous populations of interacting massive agents. Due to the factors of game complexity, dimensionality d...

Full description

Saved in:
Bibliographic Details
Main Authors: Guofang Wang, Jing Fang, Lulu Jiang, Wang Yao, Ning Li
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/23/3803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060415541706752
author Guofang Wang
Jing Fang
Lulu Jiang
Wang Yao
Ning Li
author_facet Guofang Wang
Jing Fang
Lulu Jiang
Wang Yao
Ning Li
author_sort Guofang Wang
collection DOAJ
description Multi-population mean-field game is a critical subclass of mean-field games (MFGs). It is a theoretically feasible multi-agent model for simulating and analyzing the game between multiple heterogeneous populations of interacting massive agents. Due to the factors of game complexity, dimensionality disaster and disturbances should be taken into account simultaneously to solve the multi-population high-dimensional stochastic MFG problem, which is a great challenge. We present CA-Net, a coupled alternating neural network approach for tractably solving multi-population high-dimensional MFGs. First, we provide a universal modeling framework for large-scale heterogeneous multi-agent game systems, which is strictly expressed as a multi-population MFG problem. Next, we generalize the potential variational primal–dual structure that MFGs exhibit, then phrase the multi-population MFG problem as a convex–concave saddle-point problem. Last but not least, we design a generative adversarial network (GAN) with multiple generators and multiple discriminators—the solving network—which parameterizes the value functions and the density functions of multiple populations by two sets of neural networks, respectively. In multi-group quadcopter trajectory-planning numerical experiments, the convergence results of HJB residuals, control, and average speed show the effectiveness of the CA-Net algorithm, and the comparison with baseline methods—cluster game, HJB-NN, Lax–Friedrichs, ML, and APAC-Net—shows the progressiveness of our solution method.
format Article
id doaj-art-698150b4d3974eef97b162983d64b970
institution DOAJ
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-698150b4d3974eef97b162983d64b9702025-08-20T02:50:33ZengMDPI AGMathematics2227-73902024-12-011223380310.3390/math12233803Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field GamesGuofang Wang0Jing Fang1Lulu Jiang2Wang Yao3Ning Li4Marine Human Factors Engineering Laboratory, China Institute of Marine Technology and Economy, Beijing 100081, ChinaMarine Human Factors Engineering Laboratory, China Institute of Marine Technology and Economy, Beijing 100081, ChinaMarine Human Factors Engineering Laboratory, China Institute of Marine Technology and Economy, Beijing 100081, ChinaInstitute of Artificial Intelligence, Beihang University, Beijing 100191, ChinaMarine Human Factors Engineering Laboratory, China Institute of Marine Technology and Economy, Beijing 100081, ChinaMulti-population mean-field game is a critical subclass of mean-field games (MFGs). It is a theoretically feasible multi-agent model for simulating and analyzing the game between multiple heterogeneous populations of interacting massive agents. Due to the factors of game complexity, dimensionality disaster and disturbances should be taken into account simultaneously to solve the multi-population high-dimensional stochastic MFG problem, which is a great challenge. We present CA-Net, a coupled alternating neural network approach for tractably solving multi-population high-dimensional MFGs. First, we provide a universal modeling framework for large-scale heterogeneous multi-agent game systems, which is strictly expressed as a multi-population MFG problem. Next, we generalize the potential variational primal–dual structure that MFGs exhibit, then phrase the multi-population MFG problem as a convex–concave saddle-point problem. Last but not least, we design a generative adversarial network (GAN) with multiple generators and multiple discriminators—the solving network—which parameterizes the value functions and the density functions of multiple populations by two sets of neural networks, respectively. In multi-group quadcopter trajectory-planning numerical experiments, the convergence results of HJB residuals, control, and average speed show the effectiveness of the CA-Net algorithm, and the comparison with baseline methods—cluster game, HJB-NN, Lax–Friedrichs, ML, and APAC-Net—shows the progressiveness of our solution method.https://www.mdpi.com/2227-7390/12/23/3803multi-population modelmean-field game (MFG)high-dimensional solution spacegenerative adversarial network
spellingShingle Guofang Wang
Jing Fang
Lulu Jiang
Wang Yao
Ning Li
Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games
Mathematics
multi-population model
mean-field game (MFG)
high-dimensional solution space
generative adversarial network
title Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games
title_full Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games
title_fullStr Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games
title_full_unstemmed Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games
title_short Coupled Alternating Neural Networks for Solving Multi-Population High-Dimensional Mean-Field Games
title_sort coupled alternating neural networks for solving multi population high dimensional mean field games
topic multi-population model
mean-field game (MFG)
high-dimensional solution space
generative adversarial network
url https://www.mdpi.com/2227-7390/12/23/3803
work_keys_str_mv AT guofangwang coupledalternatingneuralnetworksforsolvingmultipopulationhighdimensionalmeanfieldgames
AT jingfang coupledalternatingneuralnetworksforsolvingmultipopulationhighdimensionalmeanfieldgames
AT lulujiang coupledalternatingneuralnetworksforsolvingmultipopulationhighdimensionalmeanfieldgames
AT wangyao coupledalternatingneuralnetworksforsolvingmultipopulationhighdimensionalmeanfieldgames
AT ningli coupledalternatingneuralnetworksforsolvingmultipopulationhighdimensionalmeanfieldgames