A Bayesian optimization approach to find Nash equilibria

11/08/2016
by   Victor Picheny, et al.
0

Game theory finds nowadays a broad range of applications in engineering and machine learning. However, in a derivative-free, expensive black-box context, very few algorithmic solutions are available to find game equilibria. Here, we propose a novel Gaussian-process based approach for solving games in this context. We follow a classical Bayesian optimization framework, with sequential sampling decisions based on acquisition functions. Two strategies are proposed, based either on the probability of achieving equilibrium or on the Stepwise Uncertainty Reduction paradigm. Practical and numerical aspects are discussed in order to enhance the scalability and reduce computation time. Our approach is evaluated on several synthetic game problems with varying number of players and decision space dimensions. We show that equilibria can be found reliably for a fraction of the cost (in terms of black-box evaluations) compared to classical, derivative-based algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/27/2018

Approximating Nash Equilibria for Black-Box Games: A Bayesian Optimization Approach

Game theory has emerged as a powerful framework for modeling a large ran...
research
11/15/2018

A Bayesian optimization approach to compute the Nash equilibria of potential games using bandit feedback

Computing Nash equilibria for strategic multi-agent systems is challengi...
research
11/23/2020

Pareto-efficient Acquisition Functions for Cost-Aware Bayesian Optimization

Bayesian optimization (BO) is a popular method to optimize expensive bla...
research
10/22/2021

Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes

In Bayesian Optimization (BO) we study black-box function optimization w...
research
02/02/2017

Sensitivity Analysis of Expensive Black-Box Systems Using Metamodeling

Simulations are becoming ever more common as a tool for designing comple...
research
05/11/2017

Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search

Computational models in fields such as computational neuroscience are of...
research
06/10/2020

Robust Spammer Detection by Nash Reinforcement Learning

Online reviews provide product evaluations for customers to make decisio...

Please sign up or login with your details

Forgot password? Click here to reset