@InProceedings{claus98a,
  author =	 {Caroline Claus and Craig Boutilier},
  title =	 {The Dynamics of Reinforcement Learning in
                  Cooperative Multiagent Systems},
  booktitle =	 {Proceedings of the Fifteenth National Conference on
                  Artificial Intelligence},
  pages =	 {746--752},
  year =	 1998,
  abstract =	 {Reinforcement learning can provide a robust and
                  natural means for agents to learn how to coordinate
                  their action choices in multiagent systems. We
                  examine some of the factors that can influence the
                  dynamics of the learning process in such a
                  setting. We first distinguish reinforcement learners
                  that are unaware of (or ignore) the presence of
                  other agents from those that explicitly attempt to
                  learn the value of joint actions and the strategies
                  of their counterparts. We study (a simple form of)
                  Q-learning in cooperative multiagent systems under
                  these two perspectives, focusing on the influence of
                  that game structure and exploration strategies on
                  convergence to (optimal and suboptimal) Nash
                  equilibria. We then propose alternative optimistic
                  exploration strategies that increase the likelihood
                  of convergence to an optimal equilibrium.},
  keywords = 	 {multiagent learning reinforcement},
  url = 	 {http://jmvidal.cse.sc.edu/library/claus98a.pdf},
  googleid = 	 {m-nb1xiX8pgJ:scholar.google.com/},
  citeseer = 	 {claus98dynamics.html},
  cluster = 	 {11021037371085547931}
}