TY - JOUR
T1 - Multi-agent learning for engineers
AU - Mannor, Shie
AU - Shamma, Jeff S.
N1 - Funding Information:
✩ Research supported by Natural Sciences and Engineering Research Council of Canada, NSF grant #ECS-0501394, AFOSR/MURI grant #F49620-01-1-0361, and ARO grant #W911NF-04-1-0316. * Corresponding author. E-mail addresses: [email protected] (S. Mannor), [email protected] (J.S. Shamma).
Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
PY - 2007/5
Y1 - 2007/5
N2 - As suggested by the title of Shoham, Powers, and Grenager's position paper [Y. Shoham, R. Powers, T. Grenager, If multi-agent learning is the answer, what is the question? Artificial Intelligence 171 (7) (2007) 365-377, this issue], the ultimate lens through which the multi-agent learning framework should be assessed is "what is the question?". In this paper, we address this question by presenting challenges motivated by engineering applications and discussing the potential appeal of multi-agent learning to meet these challenges. Moreover, we highlight various differences in the underlying assumptions and issues of concern that generally distinguish engineering applications from models that are typically considered in the economic game theory literature.
AB - As suggested by the title of Shoham, Powers, and Grenager's position paper [Y. Shoham, R. Powers, T. Grenager, If multi-agent learning is the answer, what is the question? Artificial Intelligence 171 (7) (2007) 365-377, this issue], the ultimate lens through which the multi-agent learning framework should be assessed is "what is the question?". In this paper, we address this question by presenting challenges motivated by engineering applications and discussing the potential appeal of multi-agent learning to meet these challenges. Moreover, we highlight various differences in the underlying assumptions and issues of concern that generally distinguish engineering applications from models that are typically considered in the economic game theory literature.
KW - Cooperative control
KW - Distributed control
KW - Learning in games
KW - Multi-agent systems
KW - Nash equilibrium
UR - http://www.scopus.com/inward/record.url?scp=34249048200&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34249048200&partnerID=8YFLogxK
U2 - 10.1016/j.artint.2007.01.003
DO - 10.1016/j.artint.2007.01.003
M3 - Article
AN - SCOPUS:34249048200
SN - 0004-3702
VL - 171
SP - 417
EP - 422
JO - Artificial Intelligence
JF - Artificial Intelligence
IS - 7
ER -