Autonomous learning and chaining of motor primitives using the Free Energy Principle

In this article, we apply the Free-Energy Principle to the question of motor\nprimitives learning. An echo-state network is used to generate motor\ntrajectories. We combine this network with a perception module and a controller\nthat can influence its dynamics. This new compound network permits the\nautonomous learning of a repertoire of motor trajectories. To evaluate the\nrepertoires built with our method, we exploit them in a handwriting task where\nprimitives are chained to produce long-range sequences.\n