Simulated RoboCup Soccer (2004)
The UT Austin Villa Robot Soccer Team has been very active in international RoboCup competitions for the past several years, and have therefore built up a great deal of expertise in the domain of Robot Soccer and the subtask of keepaway. Reinforcement Learning often plays an important role in the success of these soccer players. Links to several demo pages associated with Robot Soccer are provided below.

Keepaway
Keepaway Pass+GetOpen
Half Field Offense
Peter Stone pstone [at] cs utexas edu
Shivaram Kalyanakrishnan shivaram [at] cs utexas edu
Gregory Kuhlmann kuhlmann [at] cs utexas edu
Matthew Taylor taylorm [at] eecs wsu edu
Keepaway Soccer: From Machine Learning Testbed to Benchmark Peter Stone and Gregory Kuhlmann and Matthew E. Taylor and Yaxin Liu In Itsuki Noda and Adam Jacoff and Ansgar Bredenfeld and Yasutake Takahashi, editors, RoboCup-200... 2006

RoboCup as an Introduction to CS Research Peter Stone In Daniel Polani and Brett Browning and Andrea Bonarini and Kazuo Yoshida, editors, RoboCup-2003:... 2004

Reinforcement Learning for RoboCup-Soccer Keepaway Peter Stone and Richard S. Sutton and Gregory Kuhlmann Adaptive Behavior, 13(3):165-188, 2005. 2005

Learning Complementary Multiagent Behaviors: A Case Study Shivaram Kalyanakrishnan and Peter Stone In Proceedings of the RoboCup International Symposium 2009, 2009. Springer Verlag. 2009

Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study Shivaram Kalyanakrishnan and Yaxin Liu and Peter Stone In Gerhard Lakemeyer and Elizabeth Sklar and Domenico Sorenti and Tomoichi Takahashi, editors, Ro... 2007

Keepaway player framework source code, version 0.6 The Keepaway player framework is an implementation of all the low- and mid-level keepaway behaviors described in the pub...