论文标题
单调游戏中广义纳什均衡的最佳选择和跟踪
Optimal selection and tracking of generalized Nash equilibria in monotone games
论文作者
论文摘要
单调游戏理论中的一个基本开放问题是计算所有可用的纳什均衡（GNE），例如相对于系统级目标的最佳平衡。现有的寻求算法实际上已融合了任意，可能效率低下的平衡的保证。在本文中，我们通过利用固定点选择理论的结果来解决这个开放问题，进而得出了分布式算法，以计算单调游戏中最佳gne。然后，我们将技术结果扩展到时间变化的设置，并提出了一种将最佳平衡序列跟踪到渐近误差的算法，该算法取决于代理的局部计算能力。
A fundamental open problem in monotone game theory is the computation of a specific generalized Nash equilibrium (GNE) among all the available ones, e.g. the optimal equilibrium with respect to a system-level objective. The existing GNE seeking algorithms have in fact convergence guarantees toward an arbitrary, possibly inefficient, equilibrium. In this paper, we solve this open problem by leveraging results from fixed-point selection theory and in turn derive distributed algorithms for the computation of an optimal GNE in monotone games. We then extend the technical results to the time-varying setting and propose an algorithm that tracks the sequence of optimal equilibria up to an asymptotic error, whose bound depends on the local computational capabilities of the agents.
