Matthew E. Taylor's Publications

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

Towards Reinforcement Learning Representation Transfer

Matthew E. Taylor and and Peter Stone. Towards Reinforcement Learning Representation Transfer. In The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 683–685, May 2007.
AAMAS-2007.
Superseded by the symposium paper Representation Transfer for Reinforcement Learning.

Download

(unavailable)

Abstract

Transfer learning problems are typically framed as leveraging knowledge learned on a source task to improve learning on a related, but different, target task. Current transfer methods are able to successfully transfer knowledge between agents in different reinforcement learning tasks, reducing the time needed to learn the target. However, the complimentary task of representation transfer, i.e.  transferring knowledge between agents with different internal representations, has not been well explored. The goal in both types of transfer problems is the same: reduce the time needed to learn the target with transfer, relative to learning the target without transfer. This work introduces one such representation transfer algorithm which is implemented in a complex multiagent domain. Experiments demonstrate that transferring the learned knowledge between different representations is both possible and beneficial.

BibTeX Entry

@InProceedings{AAMAS07-taylorRT,
        author="Matthew E.\ Taylor and and Peter Stone",
        title="Towards Reinforcement Learning Representation Transfer",
        booktitle="The Sixth International Joint Conference on
        Autonomous Agents and Multiagent Systems",
        pages="683--685",
        month="May",year="2007", 
        abstract={Transfer learning problems are typically framed as
        leveraging knowledge learned on a source task to improve
        learning on a related, but different, target task. Current
        transfer methods are able to successfully transfer knowledge
        between agents in different reinforcement learning tasks,
        reducing the time needed to learn the target. However, the
        complimentary task of representation transfer, i.e.\
        transferring knowledge between agents with different internal
        representations, has not been well explored. The goal in both
        types of transfer problems is the same: reduce the time needed
        to learn the target with transfer, relative to learning the
        target without transfer. This work introduces one such
        representation transfer algorithm which is implemented in a
        complex multiagent domain. Experiments demonstrate that
        transferring the learned knowledge between different
        representations is both possible and beneficial.},
       wwwnote={<a
       href="http://www.aamas2007.nl/">AAMAS-2007</a>. <br>Superseded by the symposium paper <a href="http://teamcore.usc.edu/taylorm/Publications/b2hd-AAAI07-Symposium.html">Representation
       Transfer for Reinforcement Learning</a>.},
}       

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