@TechReport{	  wolpert99a,
  author =	 {David H. Wolpert and Kagan Tumer},
  title =	 {An Introduction to Collective Intelligence},
  googleid =	 {89pRsJDcBLUJ:scholar.google.com/},
  institution =	 {NASA},
  note = 	 {NASA-ARC-IC-99-63},
  year =	 1999,
  abstract =	 {This paper surveys the emerging science of how to
                  design a ``COllective INtelligence'' (COIN). A COIN
                  is a large multi-agent system where: (i) There is
                  little to no centralized communication or control;
                  and (ii) There is a provided world utility function
                  that rates the possible histories of the full
                  system. In particular, we are interested in COINs in
                  which each agent runs a reinforcement learning (RL)
                  algorithm. Rather than use a conventional modeling
                  approach (e.g., model the system dynamics, and
                  hand-tune agents to cooperate), we aim to solve the
                  COIN design problem implicitly, via the ``adaptive''
                  character of the RL algorithms of each of the
                  agents. This approach introduces an entirely new,
                  profound design problem: Assuming the RL algorithms
                  are able to achieve high rewards, what reward
                  functions for the individual agents will, when
                  pursued by those agents, result in high world
                  utility? In other words, what reward functions will
                  best ensure that we do not have phenomena like the
                  tragedy of the commons, Braess's paradox, or the
                  liquidity trap? Although still very young, research
                  specifically concentrating on the COIN design
                  problem has already resulted in successes in
                  artificial domains, in particular in packet-routing,
                  the leader-follower problem, and in variants of
                  Arthur's El Farol bar problem. It is expected that
                  as it matures and draws upon other disciplines
                  related to COINs, this research will greatly expand
                  the range of tasks addressable by human
                  engineers. Moreover, in addition to drawing on them,
                  such a fully developed science of COIN design may
                  provide much insight into other already established
                  scientific fields, such as economics, game theory,
                  and population biology},
  keywords =     {multiagent learning},
  arxiv =	 {cs.LG/9908014},
  url =		 {http://jmvidal.cse.sc.edu/library/wolpert99a.pdf},
  comment =	 {Shows how to set the agents' reward functions (using
                  the "wonderful life" reward) so that the global
                  utility is maximized. Extensive related work
                  section.},
  cluster = 	 {13043792934763354867}
}