Robust Networked Multiagent Optimization: Designing Agents to Repair Their Own Utility Functions
Robust Networked Multiagent Optimization: Designing Agents to Repair Their Own Utility Functions
复制标题
DOI：
10.1007/s13235-022-00469-5
复制
发表时间：
2022-09
影响因子：
1.5
通讯作者：
Philip N. Brown;Joshua H. Seaton;Jason R. Marden
中科院分区：
文献类型：
--
作者：
Philip N. Brown;Joshua H. Seaton;Jason R. Marden
我们研究的设置，自主代理的目的是优化一个给定的系统级目标。在这个问题的典型方法中，每个代理都被赋予了一个决策规则，该规则指定代理的选择作为与系统状态有关的相关信息的函数。系统中其他代理人的选择构成了这一信息的关键组成部分。本文考虑了一种情况下，设计的决策规则是不可实现的实现系统中，由于预期和实现的信息提供给代理之间的差异。本文的重点是开发的方法，通过这些方法，代理人可以保持系统级的性能保证，在这些意想不到的情况下，通过本地和独立的重新设计自己的决策规则。首先，我们展示了一个一般的不可能的结果，它指出，在一般情况下，没有本地的重新设计方法，可以提供任何保存系统级的性能保证，即使受影响的代理满足inconsequentiality标准。然而，然后，我们表明，当系统级的目标是子模块化的，局部重新设计的效用函数确实存在，允许名义上的性能保证优雅地降低信息被拒绝代理。也就是说，在这些子模块化设置中，代理可以独立地适应信息不一致，而不会在系统级性能方面造成太大损失。
We study settings in which autonomous agents are designed to optimize a given system-level objective. In typical approaches to this problem, each agent is endowed with a decision-making rule that specifies the agent’s choice as a function of relevant information pertaining to the system’s state. The choices of other agents in the system comprise a key component of this information. This paper considers a scenario in which the designed decision-making rules are not implementable in the realized system due to discrepancies between the anticipated and realized information available to the agents. The focus of this paper is to develop methods by which the agents can preserve system-level performance guarantees in these unanticipated scenarios through local and independent redesigns of their own decision-making rules. First, we show a general impossibility result which states that in general settings, there are no local redesign methodologies that can offer any preservation of system-level performance guarantees, even when the affected agents satisfy an inconsequentiality criterion. However, we then show that when system-level objectives are submodular, local redesigns of utility functions do exist which allow nominal performance guarantees to degrade gracefully as information is denied to agents. That is, in these submodular settings, agents can adapt to informational inconsistencies independently without incurring much loss in terms of system-level performance.