Neuro-adaptive control for searching generalized Nash equilibrium of multi-agent games: A two-stage design approach

Abstract

This paper investigates the generalized Nash equilibrium searching problem of multi-agent games over weight-unbalanced directed networks. In this problem, the feasible action set of each agent is not only constrained by private convex sets and shared coupling equality, but also constrained by its own uncertain dynamics. Moreover, the local cost function is related to both his own actions and others, and each agent is only allowed access to neighbor information. To address this problem, we propose a neuro-adaptive control strategy based on two-stage design. In the first stage of design process, an approximator with adaptive-gain is designed to generate a virtual trajectory that converges to a necessary Nash equilibrium, the compensator based on consensus-tracking is used to obtain non-neighbor information and several auxiliary state variables are used to exchange information with local neighborhoods on a digraphs to deal with equality constraints. In the second stage of the strategy, we further developed a neuro-adaptive tracking controller based on one-step design for tracking the virtual trajectory. In the controller design, the virtual control variables and the actual control laws are obtained in a collective way, without repeating the design process. We introduce a variable called the minimum learning parameter to reduce the number of online learning parameters of the neural network. By using tools from variational inequality theory and Lyapunov stability theory, we prove that the proposed control strategy can drive all agents reach Nash equilibrium. Finally, the effectiveness of control strategy is verified by simulation example.