@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
@incollection(SARA05,
        author="Alexander A.\ Sherstov and Peter Stone",
        title="Function Approximation via Tile Coding: Automating Parameter Choice",
        booktitle="SARA 2005",
        series="Lecture Notes in Artificial Intelligence",      
        editor="J.-D.\ Zucker and I.\ Saitta",
	volume="3607",
        Publisher="Springer Verlag",address="Berlin",year="2005",
	pages="194--205",
        abstract={
                  Reinforcement learning (RL) is a powerful
                  abstraction of sequential decision making that has
                  an established theoretical foundation and has proven
                  effective in a variety of small, simulated domains.
                  The success of RL on real-world problems with large,
                  often continuous state and action spaces hinges on
                  effective \emph{function approximation.} Of the many
                  function approximation schemes proposed, \emph{tile
                  coding} strikes an empirically successful balance
                  among representational power, computational cost,
                  and ease of use and has been widely adopted in
                  recent RL work. This paper demonstrates that the
                  performance of tile coding is quite sensitive to
                  parameterization. We present detailed experiments
                  that isolate the effects of parameter choices and
                  provide guidance to their setting. We further
                  illustrate that \emph{no single parameterization}
                  achieves the best performance throughout the
                  learning curve, and contribute an \emph{automated}
                  technique for adjusting tile-coding parameters
                  online. Our experimental findings confirm the
                  superiority of adaptive parameterization to fixed
                  settings. This work aims to automate the choice of
                  approximation scheme not only on a problem basis but
                  also throughout the learning process, eliminating
                  the need for a substantial tuning effort.
                 },
        wwwnote={<a href="http://sara2005.limbio-paris13.org/">SARA-05</a>.<br>
Official version from <a href="http://dx.doi.org/10.1007/11527862_14">Publisher's Webpage</a>&copy Springer-Verlag},
)