Towards robust teams with many agents
Agents in deployed multiagent systems monitor other agents to coordinate and col
laborate robustly. However, as the number of agents monitored is scaled up, two key
challenges arise: (i) the number of monitoring hypotheses to be considered can grow
exponentially in the number of agents; and (ii) agents become physically and logically
unconnected (unobservable) to their peers. This paper examines these challenges in
teams of cooperating agents, focusing on a monitoring task that is of particular impor
tance to robust teamwork: detecting disagreements among teammembers. We present
YOYO, a highly scalable disagreementdetection algorithm which guarantees sound
detection in time linear in the number of agents despite the exponential number of hy
potheses. In addition, we present new upper bounds about the number of agents that
must be monitored in a team to guarantee disagreement detection. Both YOYO and
the new bounds are explored analytically and empirically in thousands of monitoring
problems, scaled to thousands of agents.
Citation
G. Kaminka,
M. Bowling.
"Towards robust teams with many agents". Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp 739-736, July 2002.
Keywords: |
|
Category: |
In Conference |
BibTeX
@incollection{Kaminka+Bowling:AAMAS02,
author = {Gal Kaminka and Michael Bowling},
title = {Towards robust teams with many agents},
Pages = {739-736},
booktitle = {Joint Conference on Autonomous Agents and Multi-Agent Systems
(AAMAS)},
year = 2002,
}
Last Updated: March 09, 2007
Submitted by AICML Admin Assistant