Rule acquiring expert controllers

A paradigm is developed for a controller to learn to control an environment by use of a benefit measure to judge the control. Rules are acquired that fire in a stimulus-response fashion for control, and rules continue to be acquired to adapt to an evolving environment. The model includes both knowledge acquisition and skill refinement through bottom-up (data driven) learning of the top-down control strategy. It is more flexible than hardware learning systems such as ADELINE or MADELINE. The controller model self-organizes by acquiring rules, and adapts by continuing to update its rules while controlling an external environment. It does this by judging the benefit of feedback due to the selected control rules and keeping counts in cells from which a rule function is generated