@COMMENT This file was generated by bib2html.pl version 0.94
@COMMENT written by Patrick Riley
@COMMENT This file came from UT Austin Villa's publication pages at
@COMMENT http://www.cs.utexas.edu/~sbarrett/publications/?p=papers
@InProceedings{AAMAS07-kalyanakrishnan,
author="Shivaram Kalyanakrishnan and Peter Stone",
title="Batch Reinforcement Learning in a Complex Domain",
booktitle="The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems",
month="May",year="2007",
isbn = "978-81-904262-7-5",
pages = "650--657",
location = "Honolulu, Hawaii",
publisher = "ACM",
address = "New York, NY, USA",
abstract={Temporal difference reinforcement learning algorithms are
perfectly suited to autonomous agents because they learn directly from
an agent's experience based on sequential actions in the environment.
However, their most common algorithmic variants are relatively
inefficient in their use of experience data, which in many agent-based
settings can be scarce. In particular, they make just one learning
``update'' for each atomic experience. Batch reinforcement learning
algorithms, on the other hand, aim to achieve greater data efficiency
by saving experience data and using it in aggregate to make updates to
the learned policy. Their success has been demonstrated in the past on
simple domains like grid worlds and low-dimensional control
applications like pole balancing. In this paper, we compare and
contrast batch reinforcement learning algorithms with on-line
algorithms based on their empirical performance in a complex,
continuous, noisy, multiagent domain, namely RoboCup soccer Keepaway.
We find that the two batch methods we consider, Experience Replay and
Fitted Q Iteration, both yield significant gains in sample complexity,
while achieving high asymptotic performance.},
wwwnote={BEST PAPER AWARD NOMINEE.
AAMAS-2007},
}