• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Reinforcement Learning for RoboCup-Soccer Keepaway.
Peter Stone,
Richard S. Sutton, and Gregory
Kuhlmann.
Adaptive Behavior, 13(3):165–188, 2005.
Contains material that was previously published
in an ICML-2001 paper and a
RoboCup 2003 Symposium paper.
Some simulations
of keepaway referenced in the paper and keepaway software.
RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple independent agents learning simultaneously, and long and variable delays in the effects of actions. We describe our application of episodic SMDP Sarsa(lambda) with linear tile-coding function approximation and variable lambda to learning higher-level decisions in a keepaway subtask of RoboCup soccer. In keepaway, one team, ``the keepers,'' tries to keep control of the ball for as long as possible despite the efforts of ``the takers.'' The keepers learn individually when to hold the ball and when to pass to a teammate. Our agents learned policies that significantly outperform a range of benchmark policies. We demonstrate the generality of our approach by applying it to a number of task variations including different field sizes and different numbers of players on each team.
@Article{AB05,
Author="Peter Stone and Richard S. Sutton and Gregory Kuhlmann",
Title="Reinforcement Learning for {R}obo{C}up-Soccer Keepaway",
journal="Adaptive Behavior",
volume="13",number="3",
year = "2005", pages="165--188",
abstract={
RoboCup simulated soccer presents many challenges to
reinforcement learning methods, including a large state
space, hidden and uncertain state, multiple independent
agents learning simultaneously, and long and variable
delays in the effects of actions. We describe our
application of episodic SMDP Sarsa(lambda) with linear
tile-coding function approximation and variable
lambda to learning higher-level decisions in a
keepaway subtask of RoboCup soccer. In keepaway, one
team, ``the keepers,'' tries to keep control of the ball
for as long as possible despite the efforts of ``the
takers.'' The keepers learn individually when to hold
the ball and when to pass to a teammate. Our agents
learned policies that significantly outperform a range
of benchmark policies. We demonstrate the generality of
our approach by applying it to a number of task
variations including different field sizes and different
numbers of players on each team.
},
wwwnote={Contains material that was previously published in an <a href="http://www.cs.utexas.edu/~pstone/Papers/2001ml/keepaway.pdf">ICML-2001 paper </a> and a <a href="http://www.cs.utexas.edu/~pstone/Papers/2003robocup/keepaway-progress.pdf"> RoboCup 2003 Symposium paper</a>.<br>
Some <a href="http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/">simulations of keepaway</a> referenced in the paper and keepaway software.},
}
Generated by bib2html.pl (written by Patrick Riley ) on Tue Nov 19, 2024 10:24:39