@article{modelbasedpolicygradientswithparameter,
  title = {Model-Based Policy Gradients with Parameter-Based Exploration by Least-Squares Conditional Density Estimation},
  author = {Syogo Mori and Voot Tangkaratt and Tingting Zhao and Jun Morimoto and Masashi Sugiyama},
  year = {2013},
  eprint = {1307.5118},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1307.5118v1},
}