局所的交流とGP学習による状態推移を行うマルチエージェントからなるセル平面のクラスタ形成分析とその応用(一般講演1B)

抄録

This paper deals with analysis of cluster formations on planer cells consisting of multi-agents using local interactions and state transitions based on the Genetic Programming and its applications. It is shown if the states of agent are restricted to be binary, then the equilibrium is attained only in an asymptotic sense. However, in cases where the number of states is larger than one, the attainment of equilibrium is not ensured. Then, we examine the result by using the simulation studied where agents learn form past experiences based on the GP.