author =		 "Hachiya, H. and  Akiyama, T. and  Sugiyama, M. and  Peters, J.",
  year =		 "2009",
  title =		 "Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning",
  booktitle =		 "Neural Networks",
  key =			 "off-policy reinforcement learning and  value function approximation and  policy iteration and  adaptive importance sampling and  importance-weighted cross-validation and  efficient sample reuse",
  URL =			 "",
  number =		 "10",
  pages =		 "1399-1410",
  crossref =		 "p10198"