@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@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.},
}