Une approche automate cellulaire pour L’apprentissage d’un agent

Abstract

The machine learning is a field of study of artificial intelligence. The machine learning refers to the development, analysis and implementation of methods that allow a machine(in the broad sense) to evolve through a learning process , and so fulfill the tasks which are difficult or impossible to perform in more conventional algorithmic ways. We can design a machine learning system that enables a robot which has the ability to move its limbs, but does not know anything about the coordination of movement for walking, to learning to walk. The robot will begin by performing random motion, then, by privileging the movements that enable it to go forward, will gradually put in place a more and more efficient step... The objective of this work is to propose a learning approach based on cellular automaton for agent.