@InProceedings{wolpert99b,
  author =	 {David Wolpert and Kevin Wheeler and Kagan Tumer},
  title =	 {General Principles of Learning-Based Multi-Agent
                  Systems},
  googleid =	 {PG9fDQwTqX0J:scholar.google.com/},
  booktitle =	 {Proceedings of the Third International Conference on
                  Automomous Agents},
  year =	 1999,
  pages =	 {77--83},
  address =	 {Seattle, WA},
  abstract =	 {We consider the problem of how to design large
                  decentralized multi-agent systems (MAS's) in an
                  automated fashion, with little or no
                  hand-tuning. Our approach has each agent run a
                  reinforcement learning algorithm. This converts the
                  problem into one of how to automatically set/update
                  the reward functions for each of the agents so that
                  the global goal is achieved. In particular we do not
                  want the agents to ``work at cross-purposes'' as far
                  as the global goal is concerned. We use the term
                  artificial COllective INtelligence (COIN) to refer
                  to systems that embody solutions to this problem. In
                  this paper we present a summary of a mathematical
                  framework for COINs. We then investigate the
                  real-world applicability of the core concepts of
                  that framework via two computer experiments: we show
                  that our COINs perform near optimally in a difficult
                  variant of Arthur's bar problem (and in particular
                  avoid the tragedy of the commons for that problem),
                  and we also illustrate optimal performance for our
                  COINs in the leader-follower problem. },
  keywords =     {multiagent learning},
  url =		 {http://jmvidal.cse.sc.edu/library/wolpert99b.pdf},
  cluster = 	 {9054789468289986364}
}