Matthew E. Taylor's Publications

Sorted by DateClassified by Publication TypeSorted by First Author Last NameClassified by Research Category

Speeding up Reinforcement Learning with Behavior Transfer

Matthew E. Taylor and Peter Stone. Speeding up Reinforcement Learning with Behavior Transfer. In AAAI 2004 Fall Symposium on Real-life Reinforcement Learning, October 2004.
Superseded by the journal article Transfer Learning via Inter-Task Mappings for Temporal Difference Learning.

Download

[PDF]144.9kB  [postscript]520.0kB  

Abstract

Reinforcement learning (RL) methods have become popular machine learning techniques in recent years. RL has had some experimental successes and has been shown to exhibit some desirable properties in theory, but it has often been found very slow in practice. In this paper we introduce behavior transfer, a novel approach to speeding up traditional RL. We present experimental results showing a learner is able learn one task and then use behavior transfer to markedly reduce the total training time for a more complex task.

BibTeX Entry

@InProceedings(AAAI04-Symposium,
        author="Matthew E.\ Taylor and Peter Stone",
        title="Speeding up Reinforcement Learning with Behavior Transfer",
        BookTitle="AAAI 2004 Fall Symposium on
        Real-life Reinforcement Learning",
        month="October",year="2004",
        abstract={
                  Reinforcement learning (RL) methods
                  have become popular machine learning techniques in
                  recent years. RL has had some experimental successes
                  and has been shown to exhibit some desirable
                  properties in theory, but it has often been found
                  very slow in practice.  In this paper we introduce
                  \emph{behavior transfer}, a novel approach to
                  speeding up traditional RL. We present experimental
                  results showing a learner is able learn one task and
                  then use behavior transfer to markedly reduce the
                  total training time for a more complex task.
        },
  wwwnote={Superseded by the journal article <a
   href="http://teamcore.usc.edu/taylorm/Publications/b2hd-JMLR07-taylor.html">Transfer
   Learning via Inter-Task Mappings for Temporal Difference
   Learning</a>.}, 
)

Generated by bib2html.pl (written by Patrick Riley ) on Mon Apr 19, 2010 14:12:46