Keepaway soccer has been previously put forth as a emphtestbed for machine learning. Although multiple researchers have used it successfully for machine learning experiments, doing so has required a good deal of domain expertise. This paper introduces a set of programs, tools, and resources designed to make the domain easily usable for experimentation without any prior knowledge of RoboCup or the Soccer Server. In addition, we report on new experiments in the Keepaway domain, along with performance results designed to be directly comparable with future experimental results. Combined, the new infrastructure and our concrete demonstration of its use in comparative experiments elevate the domain to a machine learning emphbenchmark, suitable for use by researchers across the field.

PDF, PS, HTML

In RoboCup-2005: Robot Soccer World Cup IX, Itsuki Noda and Adam Jacoff and Ansgar Bredenfeld and Yasutake Takahashi (Eds.), Vol. 4020, pp. 93-105, Berlin 2006. Springer Verlag.

@incollection{LNAI2005-keepaway, title={Keepaway Soccer: From Machine Learning Testbed to Benchmark}, author={Peter Stone and Gregory Kuhlmann and Matthew E. Taylor and Yaxin Liu}, booktitle={RoboCup-2005: Robot Soccer World Cup IX}, volume={4020}, editor={Itsuki Noda and Adam Jacoff and Ansgar Bredenfeld and Yasutake Takahashi}, address={Berlin}, publisher={Springer Verlag}, pages={93-105}, url="http://www.cs.utexas.edu/users/ai-lab?LNAI2005-keepaway", year={2006} }