@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(AAAI05-actions,
        author="Alexander A.\ Sherstov and Peter Stone",
        title="Improving Action Selection in {MDP}'s via Knowledge Transfer",
        booktitle="Proceedings of the Twentieth National Conference on Artificial Intelligence",
        month="July",year="2005",
        abstract={
                  Temporal-difference reinforcement learning (RL) has
                  been successfully applied in several domains with
                  large \emph{state} sets. Large \emph{action} sets,
                  however, have received considerably less attention.
                  This paper demonstrates the use of knowledge
                  transfer between related tasks to accelerate
                  learning with large action sets.  We introduce
                  \emph{action transfer}, a technique that extracts
                  the actions from the \mbox{(near-)optimal} solution
                  to the first task and uses them in place of the full
                  action set when learning any subsequent tasks.  When
                  optimal actions make up a small fraction of the
                  domain's action set, action transfer can
                  substantially reduce the number of actions and thus
                  the complexity of the problem. However, action
                  transfer between \emph{dissimilar} tasks can be
                  detrimental. To address this difficulty, we
                  contribute \emph{randomized task perturbation}
                  (RTP), an enhancement to action transfer that makes
                  it robust to unrepresentative source tasks. We
                  motivate RTP action transfer with a detailed
                  theoretical analysis featuring a formalism of
                  related tasks and a bound on the suboptimality of
                  action transfer.  The empirical results in this
                  paper show the potential of RTP action transfer to
                  substantially expand the applicability of RL to
                  problems with large action sets.
                 },
        wwwnote={<a href="http://www.aaai.org/Conferences/National/2005/aaai05.html">AAAI 2005</a>},
)