arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1603.09258eess.SYcs.SY
收藏

存在扰动情况下的分布式学习

Distributed Learning in the Presence of Disturbances

Automatic Control Lab, Electrical Engineering, ETH(自动控制实验室,电气工程系,苏黎世联邦理工学院)

Chithrupa Ramesh, Marius Schmitt, John Lygeros

AI总结:

本文研究了在存在扰动情况下,多个智能体如何通过分布式方法学习最优行动组合。提出改进算法在扰动下仍能学习帕累托最优解,并应用于交通控制中的坡道协调问题。

摘要:

我们考虑了一个问题,即多个智能体必须以分布式方式学习一个行动组合,以最大化其效用之和。假设智能体对其他智能体的效用函数和行动收益毫无了解。这些假设出现在复杂系统中交互建模以及系统各组件间通信困难时。在[1]中提出了一种分布式算法,该算法在此问题设置中学习帕累托有效解。然而,该方法假设所有智能体都能选择行动,这排除了扰动的可能。在本文中,我们证明了一种改进的分布式学习算法版本能够在有限扰动集存在的情况下学习帕累托有效解。我们应用我们的方法到不同需求配置下的交通控制中的坡道协调问题。

英文摘要:

We consider a problem where multiple agents must learn an action profile that maximises the sum of their utilities in a distributed manner. The agents are assumed to have no knowledge of either the utility functions or the actions and payoffs of other agents. These assumptions arise when modelling the interactions in a complex system and communicating between various components of the system are both difficult. In [1], a distributed algorithm was proposed, which learnt Pareto-efficient solutions in this problem setting. However, the approach assumes that all agents can choose their actions, which precludes disturbances. In this paper, we show that a modified version of this distributed learning algorithm can learn Pareto-efficient solutions, even in the presence of disturbances from a finite set. We apply our approach to the problem of ramp coordination in traffic control for different demand profiles.

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。

↑