@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{ADPRL11-shimon,
	author="Shimon Whiteson and Brian Tanner and Matthew E.\ Taylor and Peter Stone", 
	title="Protecting Against Evaluation Overfitting in Empirical Reinforcement Learning",
	booktitle="{IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)",
	month="April",
	year="2011",
	abstract={
                  Empirical evaluations play an important role in
                  machine learning. However, the usefulness of any
                  evaluation depends on the \emph{empirical
                  methodology} employed. Designing good empirical
                  methodologies is difficult in part because agents
                  can \emph{overfit} test evaluations and thereby
                  obtain misleadingly high scores. We argue that
                  reinforcement learning is particularly vulnerable to
                  \emph{environment overfitting} and propose as a
                  remedy \emph{generalized methodologies}, in which
                  evaluations are based on multiple environments
                  sampled from a distribution. In addition, we
                  consider how to summarize performance when scores
                  from different environments may not have
                  commensurate values. Finally, we present
                  proof-of-concept results demonstrating how these
                  methodologies can validate an intuitively useful
                  range-adaptive tile coding method.
   },
   wwwnote={<a href="http://www.ieee-ssci.org/2011/adprl-2011">2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)</a>},
}