@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{AAMAS09-kalyanakrishnan,
author = {Shivaram Kalyanakrishnan and Peter Stone},
title = {An Empirical Analysis of Value Function-Based and Policy Search Reinforcement Learning},
booktitle = "The Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS)",
location = "Budapest, Hungary",
month = "May",
year = "2009",
pages="749--756",
location = {Budapest, Hungary},
isbn = {978-0-9817381-7-8},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
abstract = {
In several agent-oriented scenarios in the real world, an autonomous
agent that is situated in an unknown environment must learn through
a process of trial and error to take actions that result in long-term
benefit. Reinforcement Learning (or sequential decision making) is a
paradigm well-suited to this requirement. Value function-based methods
and policy search methods are contrasting approaches to solve
reinforcement learning tasks. While both classes of methods benefit
from independent theoretical analyses, these often fail to extend to
the practical situations in which the methods are deployed. We conduct
an emperical study to examine the strengths and weaknesses of these
approaches by introducing a suite of test domains that can be varied
for problem size, stochasticity, function approximation, and partial
observability. Our results indicate clear patterns in the domain
characteristics for which each class of methods excels. We
investigate whether their strengths can be combine, and develop an
approach to achieve that purpose. The effectiveness of this approach
is also demonstrated on the challenging benchmark task of robot soccer
Keepaway. We highlight several lines of inquiry that emanate from this
study.
},
wwwnote={AAMAS 2009},
}