Robust Agent Teams via Socially-Attentive Monitoring

TL;DR

This paper investigates how much monitoring is necessary for effective failure detection in multi-agent teams, proposing socially-attentive algorithms that balance correctness, completeness, and monitoring effort in dynamic environments.

Contribution

It introduces and empirically evaluates socially-attentive monitoring algorithms that efficiently detect teamwork failures with limited monitoring, contrasting centralized and distributed approaches.

Findings

Distributed monitoring achieves correct and complete failure detection with limited knowledge.

Centralized algorithms trade correctness for completeness and require monitoring all agents.

The system generalizes to various coordination relationships and supports online and offline diagnosis.

Abstract

Agents in dynamic multi-agent environments must monitor their peers to execute individual and group plans. A key open question is how much monitoring of other agents' states is required to be effective: The Monitoring Selectivity Problem. We investigate this question in the context of detecting failures in teams of cooperating agents, via Socially-Attentive Monitoring, which focuses on monitoring for failures in the social relationships between the agents. We empirically and analytically explore a family of socially-attentive teamwork monitoring algorithms in two dynamic, complex, multi-agent domains, under varying conditions of task distribution and uncertainty. We show that a centralized scheme using a complex algorithm trades correctness for completeness and requires monitoring all teammates. In contrast, a simple distributed teamwork monitoring algorithm results in correct and complete detection of teamwork failures, despite relying on limited, uncertain knowledge, and monitoring only key agents in a team. In addition, we report on the design of a socially-attentive monitoring system and demonstrate its generality in monitoring several coordination relationships, diagnosing detected failures, and both on-line and off-line applications.