Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints [chapter]

Pierre-Yves Oudeyer, Adrien Baranes, Frédéric Kaplan
2012 Intrinsically Motivated Learning in Natural and Artificial Systems  
Open-ended exploration and learning in the real world is a major challenge of developmental robotics. Three properties of real-world sensorimotor spaces provide important conceptual and technical challenges: unlearnability, high-dimensionality and unboundedness. In this chapter, we argue that exploration in such spaces needs to be constrained and guided by several combined developmental mechanisms. While intrinsic motivation, i.e. curiosity-driven learning, is a key mechanism to address this
more » ... llenge, it has to be complemented and integrated with other developmental constraints, in particular: sensorimotor primitives and embodiment, task space representations, maturational processes (i.e. adaptive changes of the embodied sensorimotor apparatus), and social guidance. We illustrate and discuss the potential of such an integration of developmental mechanisms in several robot learning experiments.
doi:10.1007/978-3-642-32375-1_13 fatcat:vpif7oyjx5hwha6plxbkugn4h4