Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems

11/19/2020
by   Yujie Tang, et al.
0

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. Such problems arise in many applications, such as distributed routing control, wind farm operation, etc. In many of these problems, gradient information may not be readily available, and the agents may only observe their local costs incurred by their actions as a feedback to determine their new actions. In this paper, we propose a zeroth-order feedback optimization scheme for the class of problems we consider, and provide explicit complexity bounds for both the convex and nonconvex settings 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2020

Cooperative Path Integral Control for Stochastic Multi-Agent Systems

A distributed stochastic optimal control solution is presented for coope...
research
10/09/2021

Multi-Agent MDP Homomorphic Networks

This paper introduces Multi-Agent MDP Homomorphic Networks, a class of n...
research
04/09/2019

Gradient-Free Multi-Agent Nonconvex Nonsmooth Optimization

In this paper, we consider the problem of minimizing the sum of nonconve...
research
04/30/2012

QD-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations

The paper considers a class of multi-agent Markov decision processes (MD...
research
10/27/2017

Zeroth Order Nonconvex Multi-Agent Optimization over Networks

In this paper we consider distributed optimization problems over a multi...
research
06/09/2011

Collective Intelligence, Data Routing and Braess' Paradox

We consider the problem of designing the the utility functions of the ut...
research
06/24/2016

Relating Knowledge and Coordinated Action: The Knowledge of Preconditions Principle

The Knowledge of Preconditions principle (KoP) is proposed as a widely a...

Please sign up or login with your details

Forgot password? Click here to reset