neural networks research group
areas
people
projects
demos
publications
software/data
Accelerating Search with Transferred Heuristics (2007)
Matthew E. Taylor
and
Gregory Kuhlmann
and
Peter Stone
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.
View:
PDF
,
PS
,
HTML
Citation:
In
ICAPS-07 workshop on AI Planning and Learning
, September 2007.
Bibtex:
@inproceedings{ICAPS07WS-taylor, title={Accelerating Search with Transferred Heuristics}, author={Matthew E. Taylor and Gregory Kuhlmann and Peter Stone}, booktitle={ICAPS-07 workshop on AI Planning and Learning}, month={September}, url="http://nn.cs.utexas.edu/?ICAPS07WS-taylor", year={2007} }
People
Gregory Kuhlmann
kuhlmann [at] cs utexas edu
Peter Stone
pstone [at] cs utexas edu
Matthew Taylor
taylorm [at] eecs wsu edu
Areas of Interest
Transfer Learning
Other Areas