Development, learning and evolution in animats

Describes the works of Boers and Kuiper (1992), Vaario (1992, 1994), Nolfi and Parisi (1991), Gruau (1992), and Dellaert and Beer (1994), which all evolve the developmental program of an artificial nervous system. The potentialities of these approaches for automatically devising a control architecture linking the perceptions and the actions of an animat are then discussed, together with their possible contributions to the fundamental issue of assessing the adaptive values of development, learning and evolution.