Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Accelerating Search with Transferred Heuristics

Matthew E. Taylor, Gregory Kuhlmann, and Peter Stone. Accelerating Search with Transferred Heuristics. In ICAPS-07 workshop on AI Planning and Learning, September 2007.
ICAPS 2007 workshop on AI Planning and Learning

Download

[PDF]139.9kB  [postscript]215.4kB  

Abstract

A common goal for transfer learning research is to show that a learner can solve a source task and then leverage the learned knowledge to solve a target task faster than if it had learned the target task directly. A more difficult goal is to reduce the total training time so that learning the source task and target task is faster than learning only the target task. This paper addresses the second goal by proposing a transfer hierarchy for 2-player games. Such a hierarchy orders games in terms of relative solution difficulty and can be used to select source tasks that are faster to learn than a given target task. We empirically test transfer between two types of tasks in the General Game Playing domain, the testbed for an international competition developed at Stanford. Our results show that transferring learned search heuristics from tasks in different parts of the hierarchy can significantly speed up search even when the source and target tasks differ along a number of important dimensions.

BibTeX Entry

@inproceedings(ICAPS07WS-taylor,
  author="Matthew E.\ Taylor and Gregory Kuhlmann and Peter Stone",
  title="Accelerating Search with Transferred Heuristics",
  Booktitle="{ICAPS}-07 workshop on AI Planning and Learning",
  month="September",year="2007",
  abstract={A common goal for transfer learning research is to show
    that a learner can solve a source task and then leverage the
    learned knowledge to solve a target task faster than if it had
    learned the target task directly. A more difficult goal is to
    reduce the total training time so that learning the source task
    and target task is faster than learning only the target task. This
    paper addresses the second goal by proposing a transfer hierarchy
    for 2-player games. Such a hierarchy orders games in terms of
    relative solution difficulty and can be used to select source
    tasks that are faster to learn than a given target task. We
    empirically test transfer between two types of tasks in the
    General Game Playing domain, the testbed for an international
    competition developed at Stanford. Our results show that
    transferring learned search heuristics from tasks in different
    parts of the hierarchy can significantly speed up search even when
    the source and target tasks differ along a number of important
    dimensions.},
        wwwnote={<a href="http://www.cs.umd.edu/users/ukuter/icaps07aipl/">ICAPS 2007 workshop on AI Planning and Learning</a>},
)

Generated by bib2html.pl (written by Patrick Riley ) on Fri Sep 05, 2014 12:17:35