Peter Stone's Selected Publications

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


Cross-Domain Transfer for Reinforcement Learning

Cross-Domain Transfer for Reinforcement Learning.
Matthew E. Taylor and Peter Stone.
In Proceedings of the Twenty-Fourth International Conference on Machine Learning, June 2007.
ICML 2007

Download

[PDF]220.7kB  [postscript]325.4kB  

Abstract

A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcement learning settings have shown considerable promise, but they typically transfer between pairs of very similar tasks. This work introduces Rule Transfer, a transfer algorithm that first learns rules to summarize a source task policy and then leverages those rules to learn faster in a target task. This paper demonstrates that Rule Transfer can effectively speed up learning in Keepaway, a benchmark RL problem in the robot soccer domain, based on experience from source tasks in the gridworld domain. We empirically show, through the use of three distinct transfer metrics, that Rule Transfer is effective across these domains.

BibTeX Entry

@InProceedings(ICML07-taylor,
         author="Matthew E.\ Taylor and Peter Stone",
         title="Cross-Domain Transfer for Reinforcement Learning",
         booktitle="Proceedings of the Twenty-Fourth International
          Conference on Machine Learning",
         month="June",year="2007",
         abstract="A typical goal for transfer learning algorithms is
           to utilize knowledge gained in a source task to learn a
           target task faster. Recently introduced transfer methods in
           reinforcement learning settings have shown considerable
           promise, but they typically transfer between pairs of very
           similar tasks. This work introduces \emph{Rule Transfer}, a
           transfer algorithm that first learns rules to summarize a
           source task policy and then leverages those rules to learn
           faster in a target task. This paper demonstrates that Rule
           Transfer can effectively speed up learning in Keepaway, a
           benchmark RL problem in the robot soccer domain, based on
           experience from source tasks in the gridworld domain. We
           empirically show, through the use of three distinct transfer
           metrics, that Rule Transfer is effective across these
           domains.",
         wwwnote={<a href="http://oregonstate.edu/conferences/icml2007">ICML
          2007</a>},
)

Generated by bib2html.pl (written by Patrick Riley ) on Mon Mar 11, 2024 23:59:14