Matthew E. Taylor's Publications

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

Transfer Learning for Policy Search Methods

Matthew E. Taylor, Shimon Whiteson, and Peter Stone. Transfer Learning for Policy Search Methods. In ICML workshop on Structural Knowledge Transfer for Machine Learning, June 2006.
ICML-2006 workshop on Structural Knowledge Transfer for Machine Learning.
Superseded by the conference paper Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning.

Download

(unavailable)

Abstract

An ambitious goal of transfer learning is to learn a task faster after training on a different, but related, task. In this paper we extend a previously successful temporal difference approach to transfer in reinforcement learning tasks to work with policy search. In particular, we show how to construct a mapping to translate a population of policies trained via genetic algorithms (GAs) from a source task to a target task. Empirical results in robot soccer Keepaway, a standard RL benchmark domain, demonstrate that transfer via inter-task mapping can markedly reduce the time required to learn a second, more complex, task.

BibTeX Entry

@inproceedings(ICML06-taylor,
  author="Matthew E.\ Taylor and Shimon Whiteson and Peter Stone",
  title="Transfer Learning for Policy Search Methods",
  Booktitle="{ICML} workshop on Structural Knowledge Transfer for Machine Learning",
  month="June",year="2006",
        abstract={
                  An ambitious goal of \emph{transfer learning} is to
                  learn a task faster after training on a different,
                  but related, task.  In this paper we extend a
                  previously successful \emph{temporal difference}
                  approach to transfer in \emph{reinforcement
                  learning} tasks to work with policy search.  In
                  particular, we show how to construct a mapping to
                  translate a population of policies trained via
                  genetic algorithms (GAs) from a \emph{source} task
                  to a \emph{target} task.  Empirical results in robot
                  soccer Keepaway, a standard RL benchmark domain,
                  demonstrate that \emph{transfer via inter-task
                  mapping} can markedly reduce the time required to
                  learn a second, more complex, task.
        },
  wwwnote={<a
  href="http://www.cs.utexas.edu/~banerjee/icmlws06/">ICML-2006 workshop on Structural Knowledge Transfer for Machine Learning</a>.<br> Superseded by the conference paper <a href="http://teamcore.usc.edu/taylorm/Publications/b2hd-AAMAS07-taylor.html">Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning</a>.},
)

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