arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.04972eess.SYcs.GTcs.SYmath.OC
收藏

基于模拟的网络上分布式协调最大化

Simulation-based Distributed Coordination Maximization over Networks

King’s College London(伦敦国王学院);Korea Advanced Institute of Science and Technology(韩国科学技术院)

Hyeryung Jang, Jinwoo Shin, Yung Yi

AI总结:

本文提出三种基于模拟的分布式算法,通过马尔可夫链模拟实现收敛,解决网络协调优化问题,展示收敛性、最优性和效率与收敛速度的权衡。

摘要:

在各种在线/离线多智能体网络环境中,系统通过协调两个交互智能体的动作而受益,但需要付出协调成本。本文首先提出一个优化问题,捕捉协调收益与节点激活成本之间的关系。由于目标收益依赖于相邻节点长期时间部分的耦合激活,因此难以用标准拉格朗日对偶理论进行分布式求解。本文提出三种基于模拟的分布式算法,具有不同的更新规则,仅需单跳消息传递和本地观察信息。关键思想是通过不完全运行马尔可夫链模拟实现分布式性,从而保证收敛到最优解。接着,我们提供了一个博弈论框架,从不同角度解释所提算法。我们人工选择收益函数,使得博弈的纳什均衡渐近等于社会最优点,即无价格厌恶。我们展示两种随机近似变体的标准博弈学习动态与从优化视角开发的两种算法重合。最后,通过大量模拟验证了理论发现,包括收敛性、最优性和效率与收敛速度的权衡。

英文摘要:

In various online/offline multi-agent networked environments, it is very popular that the system can benefit from coordinating actions of two interacting agents at some cost of coordination. In this paper, we first formulate an optimization problem that captures the amount of coordination gain at the cost of node activation over networks. This problem is challenging to solve in a distributed manner, since the target gain is a function of the long-term time portion of the inter-coupled activations of two adjacent nodes, and thus a standard Lagrange duality theory is hard to apply to obtain a distributed decomposition as in the standard Network Utility Maximization. In this paper, we propose three simulation-based distributed algorithms, each having different update rules, all of which require only one-hop message passing and locally-observed information. The key idea for being distributedness is due to a stochastic approximation method that runs a Markov chain simulation incompletely over time, but provably guarantees its convergence to the optimal solution. Next, we provide a game-theoretic framework to interpret our proposed algorithms from a different perspective. We artificially select the payoff function, where the game's Nash equilibrium is asymptotically equal to the socially optimal point, i.e., no Price-of-Anarchy. We show that two stochastically-approximated variants of standard game-learning dynamics overlap with two algorithms developed from the optimization perspective. Finally, we demonstrate our theoretical findings on convergence, optimality, and further features such as a trade-off between efficiency and convergence speed through extensive simulations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑