Goal-directed behaviours by reinforcement learning

The development of a high potential for out-door or hostile environment ability necessitates an adaptive and versatile control system in order to avoid the difficulties of complex and unpredictable behaviour modelling. Self-organisation allows artificial machines to approach these goals. For that, reinforcement methods are investigated: considering that the relations between the task to perform and the environment may act as a supervisor, efficient learning is performed. Starting from a very simple structure inspired by insect behaviour, the study presented in this paper is devoted to a neural-network-based control system which allows a simulated six-legged robot to walk and avoid obstacles even when it is partially damaged. (C) 1999 Elsevier Science B.V. All rights reserved.