• Classified by Research Category • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Peter Stone and Richard S. Sutton.
Scaling Reinforcement Learning toward RoboCup Soccer. In Proceedings of the Eighteenth International Conference
on Machine Learning, pp. 537–544, Morgan Kaufmann, San Francisco, CA, 2001.
ICML-2001
Extended version(under review for journal
publication) (pdf version). Most of the
content is citable either in this ICML paper or in our follow-up
paper.
Some simulations of keepaway
referenced in the paper.
[PDF]263.7kB [postscript]1.1MB
RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple agents, 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, while the takers learn when to charge the ball-holder and when to cover possible passing lanes. Our agents learned policies that significantly out-performed 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.
@InProceedings(ICML2001,
Author="Peter Stone and Richard S. Sutton",
Title="Scaling Reinforcement Learning toward {R}obo{C}up Soccer",
BookTitle="Proceedings of the Eighteenth International Conference on Machine Learning",
publisher = "Morgan Kaufmann, San Francisco, CA",
pages = "537--544",
year = "2001",
abstract={
RoboCup simulated soccer presents many challenges to
reinforcement learning methods, including a large state
space, hidden and uncertain state, multiple agents, 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, while the takers learn when to
charge the ball-holder and when to cover possible
passing lanes. Our agents learned policies that
significantly out-performed 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={<a href="http://www.ecn.purdue.edu/ICML2001/">ICML-2001</a><br>
Some <a href="http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/">simulations of keepaway</a> referenced in the paper.},
)
Generated by bib2html.pl (written by Patrick Riley ) on Sat Dec 25, 2004 10:34:31