UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Keepaway Soccer: From Machine Learning Testbed to Benchmark (2006)
Peter Stone
,
Gregory Kuhlmann
,
Matthew E. Taylor
, and
Yaxin Liu
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.
View:
PDF
,
PS
,
HTML
Citation:
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.
Bibtex:
@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} }
People
Gregory Kuhlmann
Ph.D. Alumni
kuhlmann [at] cs utexas edu
Yaxin Liu
Postdoctoral Alumni
Peter Stone
Faculty
pstone [at] cs utexas edu
Matthew Taylor
Ph.D. Alumni
taylorm [at] eecs wsu edu
Areas of Interest
Other Areas
Reinforcement Learning
Simulated Robot Soccer
Demos
Simulated RoboCup Soccer
2004
Labs
Learning Agents