arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.06287math.OCcs.GTcs.SYeess.SY
收藏

分布式控制与博弈设计:从策略型智能体到可编程机器

Distributed control and game design: From strategic agents to programmable machines

Dario Paccagnan

AI总结:

本论文研究无中心权威下的大规模系统协调,针对非合作决策问题提出均衡分配效率条件及可扩展算法,并针对大规模合作问题引入基于线性规划的新框架以设计智能体效用,使均衡配置近似最优。

摘要:

大规模系统预计将极大地影响我们未来的生活,这得益于其广泛的应用,包括协作机器人、按需出行、资源分配和供应链管理。尽管技术发展为实现此类未来系统铺平了道路,但我们在如何协调各个组件以实现期望的全局目标方面仍存在有限的认知。本论文致力于在没有集中式权威的情况下,分析和协调大规模系统。\n在本论文的第一部分,我们考虑非合作决策问题,其中每个智能体的目标都是总体行为的函数。首先,我们比较了均衡分配与最优分配的性能,并提出了所有均衡分配均具有效率的条件。为此,我们证明了一个新的结论,界定了Nash均衡与Wardrop均衡下策略之间的距离,这可能具有独立的研究价值。其次,我们展示了如何推导出可扩展的算法,以引导智能体达到均衡分配。\n在本论文的第二部分,我们考虑大规模合作问题,其中需要将若干智能体分配给一组资源,目标是共同最大化给定的次模或超模集合函数。由于这类问题在计算上难以处理,我们旨在推导出易于处理的算法以获得近似解。我们从博弈论的角度来处理该问题并提出以下疑问:我们应如何设计智能体的效用,使得任何均衡配置都几乎是最优的?为了回答这个问题,我们引入了一个新颖的框架,该框架允许通过一个易于处理的线性规划来表征和优化系统性能,将其作为所选效用的函数。

英文摘要:

Large scale systems are forecasted to greatly impact our future lives thanks to their wide ranging applications including cooperative robotics, mobility on demand, resource allocation, supply chain management. While technological developments have paved the way for the realization of such futuristic systems, we have a limited grasp on how to coordinate the individual components to achieve the desired global objective. This thesis deals with the analysis and coordination of large scale systems without the need of a centralized authority. In the first part of this thesis, we consider non-cooperative decision making problems where each agent's objective is a function of the aggregate behavior of the population. First, we compare the performance of an equilibrium allocation with that of an optimal allocation and propose conditions under which all equilibrium allocations are efficient. Towards this goal, we prove a novel result bounding the distance between the strategies at a Nash and Wardrop equilibrium that might be of independent interest. Second, we show how to derive scalable algorithms that guide agents towards an equilibrium allocation. In the second part of this thesis, we consider large-scale cooperative problems, where a number of agents need to be allocated to a set of resources with the goal of jointly maximizing a given submodular or supermodular set function. Since this class of problems is computationally intractable, we aim at deriving tractable algorithms for attaining approximate solutions. We approach the problem from a game-theoretic perspective and ask the following: how should we design agents' utilities so that any equilibrium configuration is almost optimal? To answer this question we introduce a novel framework that allows to characterize and optimize the system performance as a function of the chosen utilities by means of a tractable linear program.

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。

↑