Team flowers

Overall Objectives
Scientific Foundations
Application Domains
New Results
Contracts and Grants with Industry

Section: New Results

Maturationally-Constrained Competence-Based Intrinsically Motivated Learning

Participants : Adrien Baranès, Pierre-Yves Oudeyer.

The progressive biological maturation of infants' brain, motor and sensor capabilities, introduces numerous important constraints on the learning process. Indeed, at birth, all the sensorimotor apparatus is neither precise enough, nor fast enough, to allow infants to perform complex tasks. The low visual acuity of infants, their incapacity to efficiently control distal muscles, and to detect high-frequency sounds, are examples of constraints reducing the complexity and limiting the access to the high-dimensional and unbounded space where they evolve. Maturational constraints play an important role in learning, by partially determining a developmental pathway. Numerous biological reasons are part of this process, like the brain maturation, the weakness of infants' muscles, or the development of the physiological sensory system. A particularly important family of maturational constraint induced by the brain is due to myelination. Related to the evolution of a substance called myelin, (which is) usually called white matter, the main impact of myelination is to help the information transfer in the brain by increasing the speed at which impulses propagate along axons (connections between neurons). We have focused on the myelination process for several reasons, this phenomenon being responsible for numerous maturational constraints, affecting the motor development, but also the visual or auditive acuity, by making the number of degrees-of-freedom, and the resolution of sensori-motor channels increase progressively with time, all of this effecting the efficiency and progression of learning. We have studied the coupling of intrinsic motivation with those physiological maturational constraints, arguing that both mechanisms may have complex bidirectional interactions allowing to actively control the growth of complexity in motor development. On top of the self-adaptive goal generation algorithm (SAGG), instantiating an intrinsically motivated goal exploration mechanism for motor learning of inverse models, we have introduced a functional and formal model of maturational constraints inspired by the myelination process in humans, and showed how it can be coupled with the SAGG algorithm, forming a new system called McSAGG. We then have conducted experiments to evaluate qualitative properties of these systems when applied to learning a reaching skill with an arm with initially unknown kinematics. These results were partly published in [22] .


Logo Inria