No-Regret Learning of Nash Equilibrium for Black-Box Games via Gaussian Processes
This addresses the challenge of equilibrium learning in games with limited information, though it is incremental as it builds on existing no-regret methods.
The paper tackled the problem of learning Nash equilibrium in black-box games with unknown utility functions, using a no-regret algorithm based on Gaussian processes, and achieved theoretical convergence and experimental effectiveness across various games.
This paper investigates the challenge of learning in black-box games, where the underlying utility function is unknown to any of the agents. While there is an extensive body of literature on the theoretical analysis of algorithms for computing the Nash equilibrium with complete information about the game, studies on Nash equilibrium in black-box games are less common. In this paper, we focus on learning the Nash equilibrium when the only available information about an agent's payoff comes in the form of empirical queries. We provide a no-regret learning algorithm that utilizes Gaussian processes to identify the equilibrium in such games. Our approach not only ensures a theoretical convergence rate but also demonstrates effectiveness across a variety collection of games through experimental validation.