期刊
IEEE CONTROL SYSTEMS LETTERS
卷 6, 期 -, 页码 644-649出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LCSYS.2021.3084531
关键词
Optimization; Couplings; Stochastic processes; Resource management; Distributed algorithms; Minimization; IEEE members; Optimization algorithms; large-scale systems; distributed control; stochastic optimization
资金
- European Research Council (ERC) through the European Union [638992-OPT4SMART]
This letter presents a distributed stochastic optimization framework for agents in a network to cooperatively learn an optimal policy. The proposed algorithm utilizes consensus iterations and stochastic approximation to find the optimal solution without a central coordinator, showcasing scalability properties.
In this letter we consider a distributed stochastic optimization framework in which agents in a network aim to cooperatively learn an optimal network-wide policy. The goal is to compute local functions to minimize the expected value of a given cost, subject to individual constraints and average coupling constraints. In order to handle the challenges of the distributed stochastic context, we resort to a Lagrangian duality approach that allows us to derive an associated stochastic dual problem with a separable structure. Thus, we propose a distributed algorithm, without a central coordinator, that exploits consensus iterations and stochastic approximation to find an optimal solution to the problem, with attractive scalability properties. We demonstrate convergence of the proposed scheme and validate its behavior through simulations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据