Zeroth-order feedback optimization for cooperative multi-agent systems
Zeroth-order feedback optimization for cooperative multi-agent systems
复制标题
协作多智能体系统的零阶反馈优化
DOI：
10.1016/j.automatica.2022.110741
复制
发表时间：
2023
期刊：
影响因子：
6.4
通讯作者：
Li, Na
中科院分区：
文献类型：
--
作者：
Tang, Yujie;Ren, Zhaolin;Li, Na
我们研究了一类多智能体协作优化问题，其中每个智能体都有一个局部动作向量和一个局部代价，目标是协作找到最小局部代价平均值的联合动作轮廓。我们考虑了梯度信息不容易获得的情况，智能体只观察它们的局部行为所产生的代价作为反馈来决定它们的新行为。我们提出了一种零阶反馈优化方案，并给出了具有无噪声和有噪声局部代价观测值的约束凸集的显式复杂度界。我们还简要讨论了智能体之间局部函数依赖知识的影响。通过一个分布式路由控制的算例验证了该算法的性能。
We study a class of cooperative multi-agent optimization problems, where each agent is associated with a local action vector and a local cost, and the goal is to cooperatively find the joint action profile that minimizes the average of the local costs. We consider the setting where gradient information is not readily available, and the agents only observe their local costs incurred by their actions as a feedback to determine their new actions. We propose a zeroth-order feedback optimization scheme and provide explicit complexity bounds for the constrained convex setting with noiseless and noisy local cost observations. We also discuss briefly on the impacts of knowledge of local function dependence between agents. The algorithm’s performance is justified by a numerical example of distributed routing control.