@article{qandalearningmethodsforestimating,
  title = {$Q$- and $A$-Learning Methods for Estimating Optimal Dynamic Treatment Regimes},
  author = {Phillip J. Schulte and Anastasios A. Tsiatis and Eric B. Laber and Marie Davidian},
  year = {2012},
  eprint = {1202.4177},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1202.4177v3},
}