Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Ruimeng, Long, Jihao, Zhou, Haosheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912588748554240
author Hu, Ruimeng
Long, Jihao
Zhou, Haosheng
author_facet Hu, Ruimeng
Long, Jihao
Zhou, Haosheng
contents We propose a novel neural network architecture, called Non-Trainable Modification (NTM), for computing Nash equilibria in stochastic differential games (SDGs) on graphs. These games model a broad class of graph-structured multi-agent systems arising in finance, robotics, energy, and social dynamics, where agents interact locally under uncertainty. The NTM architecture imposes a graph-guided sparsification on feedforward neural networks, embedding fixed, non-trainable components aligned with the underlying graph topology. This design enhances interpretability and stability, while significantly reducing the number of trainable parameters in large-scale, sparse settings. We theoretically establish a universal approximation property for NTM in static games on graphs and numerically validate its expressivity and robustness through supervised learning tasks. Building on this foundation, we incorporate NTM into two state-of-the-art game solvers, Direct Parameterization and Deep BSDE, yielding their sparse variants (NTM-DP and NTM-DBSDE). Numerical experiments on three SDGs across various graph structures demonstrate that NTM-based methods achieve performance comparable to their fully trainable counterparts, while offering improved computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12484
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures
Hu, Ruimeng
Long, Jihao
Zhou, Haosheng
Machine Learning
Computer Science and Game Theory
Optimization and Control
We propose a novel neural network architecture, called Non-Trainable Modification (NTM), for computing Nash equilibria in stochastic differential games (SDGs) on graphs. These games model a broad class of graph-structured multi-agent systems arising in finance, robotics, energy, and social dynamics, where agents interact locally under uncertainty. The NTM architecture imposes a graph-guided sparsification on feedforward neural networks, embedding fixed, non-trainable components aligned with the underlying graph topology. This design enhances interpretability and stability, while significantly reducing the number of trainable parameters in large-scale, sparse settings. We theoretically establish a universal approximation property for NTM in static games on graphs and numerically validate its expressivity and robustness through supervised learning tasks. Building on this foundation, we incorporate NTM into two state-of-the-art game solvers, Direct Parameterization and Deep BSDE, yielding their sparse variants (NTM-DP and NTM-DBSDE). Numerical experiments on three SDGs across various graph structures demonstrate that NTM-based methods achieve performance comparable to their fully trainable counterparts, while offering improved computational efficiency.
title Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures
topic Machine Learning
Computer Science and Game Theory
Optimization and Control
url https://arxiv.org/abs/2509.12484