On May 8, 1997 IBM's Deep Blue computer chess program had beaten chess grand master G. Kasparov in New York. On August 10, 2006 computer Chinese chess systems had also beaten grand masters marginally in Beijing. Both types of chess game systems are planned searching expert computer systems without machine learning capability. However computer GO game systems are still far behind human GO masters's capability. Therefore a machine learning game theory could be still important research in game theory. In this article a SRM machine learning game theory is introduced. The application of our game theory to Internet security, computer security, GO games, robotics, and management systems will be investigated. The general application of our game theory to business, economics, engineering, social science, and other related fields are also discussed.
[1]
E. Berlekamp,et al.
Winning Ways for Your Mathematical Plays
,
1983
.
[2]
Harold W. Kuhn.
Introduction to John von Neuman and Oskar Morgenstern's Theory of Games and Economic Behavior
,
2007
.
[3]
John von Neumann,et al.
Theory Of Self Reproducing Automata
,
1967
.
[4]
R. E. Kalman,et al.
A New Approach to Linear Filtering and Prediction Problems
,
2002
.
[5]
James Kuodo Huang,et al.
Self-reproducing learning, data mining and intelligent predictive systems
,
2005,
2005 IEEE International Conference on Granular Computing.
[6]
J. Neumann,et al.
Theory of games and economic behavior
,
1945,
100 Years of Math Milestones.