@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
@Article{Hanna_JMLR2024,
  author   = {Josiah P. Hanna and Yash Chandak and Philip S. Thomas and Martha White and Peter Stone and Scott Niekum},
  title    = {Data-Efficient Policy Evaluation Through Behavior Policy Search},
  journal = {Journal of Machine Learning Research},
  year     = {2024},
  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.
  },
  wwwnote={<a href="http://jmlr.org/papers/v25/21-0346.html">Official version</a> on publisher's website},
}