Distributed Artificial Intelligence (DAI) has
existed as a subfield of AI for less than two
decades. DAI is concerned with systems that consist
of multiple independent entities that interact in a
domain. Traditionally, DAI has been divided into two
sub-disciplines: Distributed Problem Solving (DPS)
focuses on the information management aspects of
systems with several components working together
towards a common goal; Multiagent Systems (MAS)
deals with behavior management in collections of
several independent entities, or agents. This survey
of MAS is intended to serve as an introduction to
the field and as an organizational framework. A
series of general multiagent scenarios are
presented. For each scenario, the issues that arise
are described along with a sampling of the
techniques that exist to deal with them. The
presented techniques are not exhaustive, but they
highlight how multiagent systems can be and have
been used to build complex systems. When options
exist, the techniques presented are biased towards
machine learning approaches. Additional
opportunities for applying machine learning to MAS
are highlighted and robotic soccer is presented as
an appropriate test bed for MAS. This survey does
not focus exclusively on robotic systems. However,
we believe that much of the prior research in
non-robotic MAS is relevant to robotic MAS, and we
explicitly discuss several robotic MAS, including
all of those presented in this issue.
%0 Journal Article
%1 stone00b
%A Stone, Peter
%A Veloso, Manuela M.
%D 2000
%J Autonomous Robots
%K learning multiagent survey
%N 3
%P 345--383
%T Multiagent Systems: A Survey from a Machine Learning
Perspective
%U http://jmvidal.cse.sc.edu/library/stone00a.pdf
%V 8
%X Distributed Artificial Intelligence (DAI) has
existed as a subfield of AI for less than two
decades. DAI is concerned with systems that consist
of multiple independent entities that interact in a
domain. Traditionally, DAI has been divided into two
sub-disciplines: Distributed Problem Solving (DPS)
focuses on the information management aspects of
systems with several components working together
towards a common goal; Multiagent Systems (MAS)
deals with behavior management in collections of
several independent entities, or agents. This survey
of MAS is intended to serve as an introduction to
the field and as an organizational framework. A
series of general multiagent scenarios are
presented. For each scenario, the issues that arise
are described along with a sampling of the
techniques that exist to deal with them. The
presented techniques are not exhaustive, but they
highlight how multiagent systems can be and have
been used to build complex systems. When options
exist, the techniques presented are biased towards
machine learning approaches. Additional
opportunities for applying machine learning to MAS
are highlighted and robotic soccer is presented as
an appropriate test bed for MAS. This survey does
not focus exclusively on robotic systems. However,
we believe that much of the prior research in
non-robotic MAS is relevant to robotic MAS, and we
explicitly discuss several robotic MAS, including
all of those presented in this issue.
@article{stone00b,
abstract = {Distributed Artificial Intelligence (DAI) has
existed as a subfield of AI for less than two
decades. DAI is concerned with systems that consist
of multiple independent entities that interact in a
domain. Traditionally, DAI has been divided into two
sub-disciplines: Distributed Problem Solving (DPS)
focuses on the information management aspects of
systems with several components working together
towards a common goal; Multiagent Systems (MAS)
deals with behavior management in collections of
several independent entities, or agents. This survey
of MAS is intended to serve as an introduction to
the field and as an organizational framework. A
series of general multiagent scenarios are
presented. For each scenario, the issues that arise
are described along with a sampling of the
techniques that exist to deal with them. The
presented techniques are not exhaustive, but they
highlight how multiagent systems can be and have
been used to build complex systems. When options
exist, the techniques presented are biased towards
machine learning approaches. Additional
opportunities for applying machine learning to MAS
are highlighted and robotic soccer is presented as
an appropriate test bed for MAS. This survey does
not focus exclusively on robotic systems. However,
we believe that much of the prior research in
non-robotic MAS is relevant to robotic MAS, and we
explicitly discuss several robotic MAS, including
all of those presented in this issue.},
added-at = {2009-10-14T21:07:56.000+0200},
author = {Stone, Peter and Veloso, Manuela M.},
biburl = {https://www.bibsonomy.org/bibtex/2f704a13ad88b8d4f93cd62ea78687bdd/robbel},
googleid = {2JESs73TcuQJ:scholar.google.com/},
interhash = {661c4a95c8b6290049c8b192d3898d1d},
intrahash = {f704a13ad88b8d4f93cd62ea78687bdd},
journal = {Autonomous Robots},
keywords = {learning multiagent survey},
number = 3,
pages = {345--383},
timestamp = {2009-10-14T21:08:21.000+0200},
title = {Multiagent Systems: A Survey from a Machine Learning
Perspective},
url = {http://jmvidal.cse.sc.edu/library/stone00a.pdf},
volume = 8,
year = 2000
}