The effects of inactivation of rules for knowledge acquisition

A lot of research on knowledge acquisition using genetic algorithms (GA) has been reported. The Pittsburgh approach, which is one of the effective approaches for this problem, evaluates a set of rules according to the movement of the robot. As a result, some of the rules can be meaningless, ineffective, or anomalous while the robot acquired the objective movements. The acquired rules can have low stability for a change of environment. On the other hand, the mechanisms of the biological developmental process from only one egg cell have been investigated in biology. The existence of some of the controlling genes called "homeobox genes" in DNA has been discovered in many animals including human beings. These genes are controlling activation/inactivation of other structural genes as a transcription factor in the developmental process. The biological DNA acquires the indirect design system by these homeobox genes. This paper introduces a part of the mechanism of the homeobox genes, inactivation of other structural genes, into the GA. In this method, each rule can inactivate the other rules as the situation. It is expected that this method is effective, understandable for humans, and has high stability rules. This paper applies this method to the acquisition of control rules for a mobile robot, and studies the effectiveness of this method showing the acquired rules by the simulation.