Zeroth-order feedback optimization for cooperative multi-agent systems

We study a class of cooperative multi-agent optimization problems, where each agent is associated with local action vector and cost, the goal to cooperatively find joint profile that minimizes average costs. consider setting gradient information not readily available, agents only observe their costs incurred by actions as feedback determine new actions. propose zeroth-order scheme provide explicit complexity bounds for constrained convex noiseless noisy cost observations. also discuss briefly on impacts knowledge function dependence between agents. The algorithm’s performance justified numerical example distributed routing control.