The decision process in selective attention

A learning system that can be trained to generate the necessary sequential decision policy for maneuvering through a multiple T-maze is proposed. The selectively attentive environmental learning system (SAELS) has an architecture with two types of neurally inspired learning mechanisms to model and act on its environment. The development of a correct policy of selective attention is dependent on the reinforcement the natural system receives during learning. The authors concentrate upon a specific type of reinforcement, namely, minimally descriptive, terminally applied reinforcement. It is shown that SAELS solves the temporal credit assignment problem that arises when reinforcement is only available at the end of a sequence of actions. The general requirements of a system of selective attention and how SAELS meets these requirements are discussed