A General Framework for Optimizing and Learning Nash Equilibrium
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909303038803968 |
|---|---|
| author | Zhang, Di Gu, Wei Jin, Qing |
| author_facet | Zhang, Di Gu, Wei Jin, Qing |
| contents | One key in real-life Nash equilibrium applications is to calibrate players' cost functions. To leverage the approximation ability of neural networks, we proposed a general framework for optimizing and learning Nash equilibrium using neural networks to estimate players' cost functions. Depending on the availability of data, we propose two approaches (a) the two-stage approach: we need the data pair of players' strategy and relevant function value to first learn the players' cost functions by monotonic neural networks or graph neural networks, and then solve the Nash equilibrium with the learned neural networks; (b) the joint approach: we use the data of partial true observation of the equilibrium and contextual information (e.g., weather) to optimize and learn Nash equilibrium simultaneously. The problem is formulated as an optimization problem with equilibrium constraints and solved using a modified Backpropagation Algorithm. The proposed methods are validated in numerical experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16260 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A General Framework for Optimizing and Learning Nash Equilibrium Zhang, Di Gu, Wei Jin, Qing Computer Science and Game Theory General Economics Economics One key in real-life Nash equilibrium applications is to calibrate players' cost functions. To leverage the approximation ability of neural networks, we proposed a general framework for optimizing and learning Nash equilibrium using neural networks to estimate players' cost functions. Depending on the availability of data, we propose two approaches (a) the two-stage approach: we need the data pair of players' strategy and relevant function value to first learn the players' cost functions by monotonic neural networks or graph neural networks, and then solve the Nash equilibrium with the learned neural networks; (b) the joint approach: we use the data of partial true observation of the equilibrium and contextual information (e.g., weather) to optimize and learn Nash equilibrium simultaneously. The problem is formulated as an optimization problem with equilibrium constraints and solved using a modified Backpropagation Algorithm. The proposed methods are validated in numerical experiments. |
| title | A General Framework for Optimizing and Learning Nash Equilibrium |
| topic | Computer Science and Game Theory General Economics Economics |
| url | https://arxiv.org/abs/2408.16260 |