A Decision Making Method Based on Society of Mind Theory in Multi-player Imperfect Information Games

We are concerned with a card game called Daihinmin, which is a multi-player imperfect information game. Using Marvin Minsky's "Society of Mind" theory, we attempt to model the workings of the minds of game players. The UEC Computer Daihinmin Championship is held at The University of Electro-Communications every year, to bring together competitive client programs that correspond to players of Daihinmin, and contest their strengths. In this paper, we extract the behavior of client programs from actual competition records of the computer Daihinmin, and propose a method of building a system that determines the parameters of Daihinmin agencies by machine learning.