We introduce the differential efficiency algorithm, which partitions a perc
eptive space during unsupervised learning into categories and uses them to
solve goal-planning and classification problems. This algorithm is inspired
by a biological model of the cortex proposing the cortical column as an el
ementary unit. We validate the generality of this approach by testing it on
four problems with continuous time and no reinforcement signal until the g
oal is reached (constrained object moves, Hanoi tower problem, animal contr
ol, and simple character recognition).