Learning Through Adaptive Value: A Model Working in a Variable Environment

Abstract

Adaptive value (AV) is an environment-dependent variable. Therefore learning through AV shows different behaviors depending on the environment in which the model grows. In the presented model: 1) the model receives mobile visual stimuli and it should center them in the visual field, 2) the neurons responsible for the movement of eyes, execute a mapping of the visual field taking into account the AV for each movement, 3) AV is drawn from the interaction of biological like layers evolutionarily chosen, without any planning or supervision throughout the full learning process and 4) mapping changes as a function of the environment in which the model operates being able to revert when this changes.