1[5]Riedmiller M, Merke A, Meier D. Karlsruhe brainstormers- a reinforcement learning approach to robotic soccer[DB/OL].http://illwww.ira.uka.de/-riedml/.
2[1]Noda I. Soccer sever: a tool for researches on multi-agent systems[DB/OL].http://citeseer.nj.nec.com/noda97soccer.html.
3[2]Kitano H, Tambe M, Stone P, et al. The robocup synthetic agent challenge 97[A]. RoboCup-97:Robot Soccer World Cup I[C].Berlin:Springer Verlag, 1998.62-73.
4[3]Stone P. Layered learning in multi-agent learning[D].Pittsburgh:Carnegie Mellon University, 1998.
5[4]Kaelbling P L, Littman L M, Moore W A. Reinforcement learning: a survey[J]. Journal of Artificial Intelligence, 1996,4:237-285.
