Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Gemp, Ian
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.02308
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929575194263552
author Gemp, Ian
author_facet Gemp, Ian
contents This work proposes a novel set of techniques for approximating a Nash equilibrium in a finite, normal-form game. It achieves this by constructing a new reformulation as solving a parameterized system of multivariate polynomials with tunable complexity. In doing so, it forges an itinerant loop from game theory to machine learning and back. We show a Nash equilibrium can be approximated with purely calls to stochastic, iterative variants of singular value decomposition and power iteration, with implications for biological plausibility. We provide pseudocode and experiments demonstrating solving for all equilibria of a general-sum game using only these readily available linear algebra tools.
format Preprint
id arxiv_https___arxiv_org_abs_2411_02308
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nash Equilibria via Stochastic Eigendecomposition
Gemp, Ian
Computer Science and Game Theory
Machine Learning
This work proposes a novel set of techniques for approximating a Nash equilibrium in a finite, normal-form game. It achieves this by constructing a new reformulation as solving a parameterized system of multivariate polynomials with tunable complexity. In doing so, it forges an itinerant loop from game theory to machine learning and back. We show a Nash equilibrium can be approximated with purely calls to stochastic, iterative variants of singular value decomposition and power iteration, with implications for biological plausibility. We provide pseudocode and experiments demonstrating solving for all equilibria of a general-sum game using only these readily available linear algebra tools.
title Nash Equilibria via Stochastic Eigendecomposition
topic Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/2411.02308