Shivaram Kalyanakrishnan Yaxin Liu Peter Stone Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study. 72-85 2006 conf/robocup/2006 RoboCup http://dx.doi.org/10.1007/978-3-540-74024-7_7 db/conf/robocup/robocup2006.html#KalyanakrishnanLS06