# Peter Stone's Selected Publications

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

## Improving Action Selection in MDP's via Knowledge Transfer

Alexander A. Sherstov and Peter Stone. Improving Action Selection in MDP's via Knowledge Transfer. In Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005.
AAAI 2005

### Abstract

Temporal-difference reinforcement learning (RL) has been successfully applied in several domains with large state sets. Large action sets, however, have received considerably less attention. This paper demonstrates the use of knowledge transfer between related tasks to accelerate learning with large action sets. We introduce action transfer, a technique that extracts the actions from the \mbox(near-)optimal solution to the first task and uses them in place of the full action set when learning any subsequent tasks. When optimal actions make up a small fraction of the domain's action set, action transfer can substantially reduce the number of actions and thus the complexity of the problem. However, action transfer between dissimilar tasks can be detrimental. To address this difficulty, we contribute randomized task perturbation (RTP), an enhancement to action transfer that makes it robust to unrepresentative source tasks. We motivate RTP action transfer with a detailed theoretical analysis featuring a formalism of related tasks and a bound on the suboptimality of action transfer. The empirical results in this paper show the potential of RTP action transfer to substantially expand the applicability of RL to problems with large action sets.

### BibTeX Entry

@InProceedings(AAAI05-actions,
author="Alexander A.\ Sherstov and Peter Stone",
title="Improving Action Selection in {MDP}'s via Knowledge Transfer",
booktitle="Proceedings of the Twentieth National Conference on Artificial Intelligence",
month="July",year="2005",
abstract={
Temporal-difference reinforcement learning (RL) has
been successfully applied in several domains with
large \emph{state} sets. Large \emph{action} sets,
however, have received considerably less attention.
This paper demonstrates the use of knowledge
transfer between related tasks to accelerate
learning with large action sets.  We introduce
\emph{action transfer}, a technique that extracts
the actions from the \mbox{(near-)optimal} solution
to the first task and uses them in place of the full
action set when learning any subsequent tasks.  When
optimal actions make up a small fraction of the
domain's action set, action transfer can
substantially reduce the number of actions and thus
the complexity of the problem. However, action
transfer between \emph{dissimilar} tasks can be
detrimental. To address this difficulty, we
(RTP), an enhancement to action transfer that makes
it robust to unrepresentative source tasks. We
motivate RTP action transfer with a detailed
theoretical analysis featuring a formalism of
related tasks and a bound on the suboptimality of
action transfer.  The empirical results in this
paper show the potential of RTP action transfer to
substantially expand the applicability of RL to
problems with large action sets.
},
wwwnote={<a href="http://www.aaai.org/Conferences/National/2005/aaai05.html">AAAI 2005</a>},
)


Generated by bib2html.pl (written by Patrick Riley ) on Thu Dec 01, 2016 22:58:01