@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-transfer,
        author="Matthew E.\ Taylor and Peter Stone and Yaxin Liu",
        title="Value Functions for {RL}-Based Behavior Transfer: A Comparative Study",
        booktitle="Proceedings of the Twentieth National Conference on Artificial Intelligence",
        month="July",year="2005",
        abstract={
                  Temporal difference (TD) learning methods have
                  become popular reinforcement learning techniques in
                  recent years. TD methods, relying on function
                  approximators to generalize learning to novel
                  situations, have had some experimental successes and
                  have been shown to exhibit some desirable properties
                  in theory, but have often been found slow in
                  practice. This paper presents methods for further
                  generalizing \emph{across tasks}, thereby speeding
                  up learning, via a novel form of \emph{behavior
                  transfer}.  We compare learning on a complex task
                  with three function approximators, a CMAC, a neural
                  network, and an RBF, and demonstrate that behavior
                  transfer works well with all three.  Using behavior
                  transfer, agents are able to learn one task and then
                  markedly reduce the time it takes to learn a more
                  complex task.  Our algorithms are fully implemented
                  and tested in the RoboCup-soccer keepaway domain.
                 },
        wwwnote={<a href="http://www.aaai.org/Conferences/National/2005/aaai05.html">AAAI 2005</a>},
)