@Article{wolpert01a,
  author =	 {David Wolpert and Kagan Tumer },
  title =	 {Optimal Payoff Functions for Members of Collectives},
  googleid =	 {KBsqHB4PAwAJ:scholar.google.com/},
  journal =	 {Advances in Complex Systems},
  volume = 	 {4},
  number = 	 {2--3},
  pages = 	 {265--279},
  year =	 2001,
  url =		 {http://jmvidal.cse.sc.edu/library/wolpert01a.pdf},
  abstract =	 {We consider the problem of designing (perhaps
                  massively distributed) collectives of computational
                  processes to maximize a provided ``world'' utility
                  function. We consider this problem when the behavior
                  of each process in the collective can be cast as
                  striving to maximize its own payoff utility
                  function. For such cases the central design issue is
                  how to initialize/update those payoff utility
                  functions of the individual processes so as to
                  induce behavior of the entire collective having good
                  values of the world utility. Traditional ``team
                  game'' approaches to this problem simply assign to
                  each process the world utility as its payoff utility
                  function. In previous work we used the ``Collective
                  Intelligence'' (COIN) framework to derive a better
                  choice of payoff utility functions, one that results
                  in world utility performance up to orders of
                  magnitude superior to that ensuing from use of the
                  team game utility. In this paper we extend these
                  results using a novel mathematical framework. We
                  review the derivation under that new framework of
                  the general class of payoff utility functions that
                  both i) are easy for the individual processes to try
                  to maximize, and ii) have the property that if good
                  values of them are achieved, then we are assured of
                  a high value of world utility. These are the
                  ``Aristocrat Utility" and a new variant of the
                  ``Wonderful Life Utility" that was introduced in the
                  previous COIN work. We demonstrate experimentally
                  that using these new utility functions can result in
                  significantly improved performance over that of
                  previously investigated COIN payoff utilities, over
                  and above those previous utilities' superiority to
                  the conventional team game utility. These results
                  also illustrate the substantial superiority of these
                  payoff functions to the perhaps the most natural
                  version of the economics technique of ``endogenizing
                  externalities''.},
  keywords =     {multiagent learning},
  cluster = 	 {861046926089000}
}