Tipping the Scales: Guidance and Intrinsically Motivated Behavior

We propose a novel approach to learning in autonomous robots that relies on the dynamical maintenance of an actively sensitized sensorimotor loop. Very weak learning cues are sufficient to orient a robot towards the desired behavior which is then selected from the intrinsic exploratory movements rather than imposed by a control command. The learning paradigm is a form of guided self-organization and is comple-mentary to both active and intrinsically motivated learning. We present a systematic analysis of the learning algorithm in a robot control task and demonstrate its remarkable scalabil-ity with respect to the degrees of freedom of the system.