A Constraint-Preserving Neural Network Approach for Solving Mean-Field Games Equilibrium
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909532281634816 |
|---|---|
| author | Liu, Jinwei Ren, Lu Yao, Wang Zhang, Xiao |
| author_facet | Liu, Jinwei Ren, Lu Yao, Wang Zhang, Xiao |
| contents | Neural network-based methods have demonstrated effectiveness in solving high-dimensional Mean-Field Games (MFG) equilibria, yet ensuring mathematically consistent density-coupled evolution remains a major challenge. This paper proposes the NF-MKV Net, a neural network approach that integrates process-regularized normalizing flow (NF) with state-policy-connected time-series neural networks to solve MKV FBSDEs and their associated fixed-point formulations of MFG equilibria. The method first reformulates MFG equilibria as MKV FBSDEs, embedding density evolution into equation coefficients within a probabilistic framework. Neural networks are then employed to approximate value functions and their gradients. To enforce volumetric invariance and temporal continuity, NF architectures impose loss constraints on each density transfer function. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17450 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Constraint-Preserving Neural Network Approach for Solving Mean-Field Games Equilibrium Liu, Jinwei Ren, Lu Yao, Wang Zhang, Xiao Machine Learning 68T07 I.2.6 Neural network-based methods have demonstrated effectiveness in solving high-dimensional Mean-Field Games (MFG) equilibria, yet ensuring mathematically consistent density-coupled evolution remains a major challenge. This paper proposes the NF-MKV Net, a neural network approach that integrates process-regularized normalizing flow (NF) with state-policy-connected time-series neural networks to solve MKV FBSDEs and their associated fixed-point formulations of MFG equilibria. The method first reformulates MFG equilibria as MKV FBSDEs, embedding density evolution into equation coefficients within a probabilistic framework. Neural networks are then employed to approximate value functions and their gradients. To enforce volumetric invariance and temporal continuity, NF architectures impose loss constraints on each density transfer function. |
| title | A Constraint-Preserving Neural Network Approach for Solving Mean-Field Games Equilibrium |
| topic | Machine Learning 68T07 I.2.6 |
| url | https://arxiv.org/abs/2501.17450 |