Suzhou1

Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study

Shivaram Kalyanakrishnan, Yaxin Liu, and Peter Stone. Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study. In Gerhard Lakemeyer, Elizabeth Sklar, Domenico Sorenti, and Tomoichi Takahashi, editors, RoboCup-2006: Robot Soccer World Cup X, Lecture Notes in Artificial Intelligence, pp. 72–85, Springer Verlag, Berlin, 2007.
BEST STUDENT PAPER AWARD WINNER at RoboCup International Symposium.
Some simulations referenced in the paper.

Download

[PDF]992.2kB  [postscript]1.6MB  

Abstract

We present half field offense, a novel subtask of RoboCup simulated soccer, and pose it as a problem for reinforcement learning. In this task, an offense team attempts to outplay a defense team in order to shoot goals. Half field offense extends keepaway\citeStone+SK:2005, a simpler subtask of RoboCup soccer in which one team must try to keep possession of the ball within a small rectangular region, and away from the opposing team. Both keepaway and half field offense have to cope with the usual problems of RoboCup soccer, such as a continuous state space, noisy actions, and multiple agents, but the latter is a significantly harder multiagent reinforcement learning problem because of sparse rewards, a larger state space, a richer action set, and the sheer complexity of the policy to be learned. We demonstrate that the algorithm that has been successful for keepaway is inadequate to scale to the more complex half field offense task, and present a new algorithm to address the aforementioned problems in multiagent reinforcement learning. The main feature of our algorithm is the use of inter-agent communication, which allows for more frequent and reliable learning updates. We show empirical results verifying that our algorithm registers significantly higher performance and faster learning than the earlier approach. We also assess the contribution of inter-agent communication by considering several variations of the basic learning method. This work is a step further in the ongoing challenge to learn complete team behavior for the RoboCup simulated soccer task.

BibTeX Entry

@incollection(LNAI2006-shivaram,
author="Shivaram Kalyanakrishnan and Yaxin Liu and Peter Stone",
title="Half Field Offense in {R}obo{C}up Soccer: A Multiagent Reinforcement Learning Case Study",
booktitle= "{R}obo{C}up-2006: {R}obot {S}occer {W}orld {C}up {X}",
Editor="Gerhard Lakemeyer and Elizabeth Sklar and Domenico Sorenti and Tomoichi Takahashi",
Publisher="Springer Verlag",address="Berlin",year="2007",
issn="0302-9743",
isbn="978-3-540-74023-0",
series="Lecture Notes in Artificial Intelligence",
volume="4434",
pages="72--85",
abstract={
We present half field offense, a novel subtask of
RoboCup simulated soccer, and pose it as a problem
for reinforcement learning. In this task, an
offense team attempts to outplay a defense team in
order to shoot goals. Half field offense extends
keepaway\cite{Stone+SK:2005}, a simpler subtask
of RoboCup soccer in which one team must try to keep
possession of the ball within a small rectangular
region, and away from the opposing team. Both
keepaway and half field offense have to cope with
the usual problems of RoboCup soccer, such as a
continuous state space, noisy actions, and multiple
agents, but the latter is a significantly harder
multiagent reinforcement learning problem because of
sparse rewards, a larger state space, a richer
action set, and the sheer complexity of the policy
to be learned. We demonstrate that the algorithm
that has been successful for keepaway is inadequate
to scale to the more complex half field offense
task, and present a new algorithm to address the
aforementioned problems in multiagent reinforcement
learning. The main feature of our algorithm is the
use of inter-agent communication, which allows for
more frequent and reliable learning updates. We
show empirical results verifying that our algorithm
registers significantly higher performance and
faster learning than the earlier approach. We also
assess the contribution of inter-agent communication
by considering several variations of the basic
learning method. This work is a step further in the
ongoing challenge to learn complete team behavior
for the RoboCup simulated soccer task.
},
)

Valid CSS!
Valid XHTML 1.0!