New Generation Computing, 19(2001)103-120
Ohmsha, Ltd. and Springer-Verlag
Received 20 September 2000
Revised manuscript received 16 November 2000
This article describes the issues in multiagent learning towards RoboCup, especially for the real robot leagues. First, the review of the issue in the context of the related area is given, then related works from several viewpoints are reviewed. Next, our approach towards RoboCup Initiative is introduced and finally future issues are given.
Keywords: RoboCup, Multiagent, Reinforcement Learning, State Vecor Estimation, Local Predictive Model.