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

2018/11/15 by Anup Aprem, Stephen Roberts, Aprem, Anup +1
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #Game Theory and Applications #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1811.06503

openalex publication_date 2018/11/15 · openalex created_date 2018/11/29 · openalex updated_date 2026/07/28

Abstract

Computing Nash equilibria for strategic multi-agent systems is challenging for expensive black box systems. Motivated by the ubiquity of games involving exploitation of common resources, this paper considers the above problem for potential games. We use the Bayesian optimization framework to obtain novel algorithms to solve finite (discrete action spaces) and infinite (real interval action spaces) potential games, utilizing the structure of potential games. Numerical results illustrate the efficiency of the approach in computing the Nash equilibria of static potential games and linear Nash equilibria of dynamic potential games.

Citations

• A class of games possessing pure-strategy Nash equilibria

Related

• Approximating Nash Equilibria for Black-Box Games: A Bayesian Optimization Approach
• A Bayesian optimization approach to find Nash equilibria
• Computing Nash Equilibria in Potential Games with Private Uncoupled Constraints
• Stochastic Potential Games
• A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning