@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{ICML17-Hanna,
  author = {Josiah Hanna and Philip Thomas and Peter Stone and Scott Niekum},
  title = {Data-Efficient Policy Evaluation Through Behavior Policy Search},
  booktitle = {Proceedings of the 34th International Conference on Machine Learning (ICML)},
  location = {Sydney, Australia},
  month = {August},
  year = {2017},
  abstract = {
  We consider the task of evaluating a policy for a Markov decision process
  (MDP). The standard unbiased technique for evaluating a policy is to deploy
  the policy and observe its performance. We show that the data collected from
  deploying a different policy, commonly called the behavior policy, can be
  used to produce unbiased estimates with lower mean squared error than this
  standard technique. We derive an analytic expression for the optimal behavior
  policy---the behavior policy that minimizes the mean squared error of the
  resulting estimates. Because this expression depends on terms that are
  unknown in practice, we propose a novel policy evaluation sub-problem,
  behavior policy search: searching for a behavior policy that reduces mean
  squared error. We present a behavior policy search algorithm and empirically
  demonstrate its effectiveness in lowering the mean squared error of policy
  performance estimates.
  },
}