@incollection {NIPS2003_CN16,
  author = " Gerald Tesauro",
  title = " Extending Q-Learning to General Adaptive Multi-Agent Systems",
  booktitle = "Advances in Neural Information Processing Systems 16",
  editor = "Sebastian Thrun and Lawrence Saul and Bernhard {Sch\"{o}lkopf}",
  publisher = "MIT Press",
  address = "Cambridge, MA",
  year = "2004",
  keywords = "Q-learning, reinforcement learning, multi-agent learning, Bayesian inference, stochastic games, repeated games, policy hill climbing",
  }