Combining Hebbian and reinforcement learning in a minibrain model

Abstract

A toy model of a neural network in which both Hebbian learning and reinforcement learning occur is studied. The problem of ‘path interference’, which makes that the neural net quickly forgets previously learned input–output relations is tackled by adding a Hebbian term (proportional to the learning rate ν) to the reinforcement term (proportional to δ) in the learning rule. It is shown that the number of learning steps is reduced considerably if 1/4< ν/ δ<1/2, i.e. if the Hebbian term is neither too small nor too large compared to the reinforcement term.