• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Value Functions for RL-Based Behavior Transfer: A Comparative Study.
Matthew
E. Taylor, Peter Stone, and Yaxin
Liu.
In Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005.
AAAI
2005
[PDF]147.3kB [postscript]449.9kB
Temporal difference (TD) learning methods have become popular reinforcement learning techniques in recent years. TD methods, relying on function approximators to generalize learning to novel situations, have had some experimental successes and have been shown to exhibit some desirable properties in theory, but have often been found slow in practice. This paper presents methods for further generalizing across tasks, thereby speeding up learning, via a novel form of behavior transfer. We compare learning on a complex task with three function approximators, a CMAC, a neural network, and an RBF, and demonstrate that behavior transfer works well with all three. Using behavior transfer, agents are able to learn one task and then markedly reduce the time it takes to learn a more complex task. Our algorithms are fully implemented and tested in the RoboCup-soccer keepaway domain.
@InProceedings(AAAI05-transfer,
author="Matthew E.\ Taylor and Peter Stone and Yaxin Liu",
title="Value Functions for {RL}-Based Behavior Transfer: A Comparative Study",
booktitle="Proceedings of the Twentieth National Conference on Artificial Intelligence",
month="July",year="2005",
abstract={
Temporal difference (TD) learning methods have
become popular reinforcement learning techniques in
recent years. TD methods, relying on function
approximators to generalize learning to novel
situations, have had some experimental successes and
have been shown to exhibit some desirable properties
in theory, but have often been found slow in
practice. This paper presents methods for further
generalizing \emph{across tasks}, thereby speeding
up learning, via a novel form of \emph{behavior
transfer}. We compare learning on a complex task
with three function approximators, a CMAC, a neural
network, and an RBF, and demonstrate that behavior
transfer works well with all three. Using behavior
transfer, agents are able to learn one task and then
markedly reduce the time it takes to learn a more
complex task. Our algorithms are fully implemented
and tested in the RoboCup-soccer keepaway domain.
},
wwwnote={<a href="http://www.aaai.org/Conferences/National/2005/aaai05.html">AAAI 2005</a>},
)
Generated by bib2html.pl (written by Patrick Riley ) on Sun Nov 24, 2024 20:24:56