Designing Games for Distributed Optimization
Designing Games for Distributed Optimization
复制标题
DOI：
10.1109/jstsp.2013.2246511
复制
发表时间：
2013-02
影响因子：
7.5
通讯作者：
Na Li;Jason R. Marden
中科院分区：
文献类型：
--
作者：
Na Li;Jason R. Marden
多基因系统中的核心目标是为个别代理设计地方控制法律，以确保相对于给定的系统级别目标，需要新兴的全球行为。理想情况下，系统设计师试图满足这一目标，同时根据可能的最少信息来调节每个代理的控制法。本文着重于使用游戏理论领域实现这一目标。特别是，我们得出了一种系统的方法，用于设计本地代理目标函数，以保证（i）所得的NASH均衡和系统级别目标的优化者之间的等效性，并且（ii）结果游戏具有可利用的固有结构，可以利用在分布式学习中，例如潜在游戏。然后，可以利用任何分布式学习算法完成控制设计，该算法可以保证获得已达到的游戏结构的NASH平衡。此外，在许多设置中，最终的控制器将对许多不确定性（包括异步时钟速率，信息延迟和组件故障）具有固有的稳健性。
The central goal in multiagent systems is to design local control laws for the individual agents to ensure that the emergent global behavior is desirable with respect to a given system level objective. Ideally, a system designer seeks to satisfy this goal while conditioning each agent's control law on the least amount of information possible. This paper focuses on achieving this goal using the field of game theory. In particular, we derive a systematic methodology for designing local agent objective functions that guarantees (i) an equivalence between the resulting Nash equilibria and the optimizers of the system level objective and (ii) that the resulting game possesses an inherent structure that can be exploited in distributed learning, e.g., potential games. The control design can then be completed utilizing any distributed learning algorithm which guarantees convergence to a Nash equilibrium for the attained game structure. Furthermore, in many settings the resulting controllers will be inherently robust to a host of uncertainties including asynchronous clock rates, delays in information, and component failures.