Intrinsically Motivated Learning of Real World Sensorimotor Skills with Developmental Constraints

Abstract : 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 chal- lenges: 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 in- trinsic motivation, i.e. curiosity-driven learning, is a key mechanism to address this challenge, 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.
Document type :
Book sections
Liste complète des métadonnées

Cited literature [124 references]  Display  Hide  Download

https://hal.inria.fr/hal-00788611
Contributor : Pierre-Yves Oudeyer <>
Submitted on : Thursday, February 14, 2013 - 5:06:55 PM
Last modification on : Monday, December 17, 2018 - 10:26:21 AM
Document(s) archivé(s) le : Wednesday, May 15, 2013 - 4:03:05 AM

File

OudeyerBaranesKaplan13.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00788611, version 1

Collections

Citation

Pierre-Yves Oudeyer, Adrien Baranes, Frédéric Kaplan. Intrinsically Motivated Learning of Real World Sensorimotor Skills with Developmental Constraints. Baldassarre, Gianluca and Mirolli, Marco. Intrinsically Motivated Learning in Natural and Artificial Systems, Springer, 2013. ⟨hal-00788611⟩

Share

Metrics

Record views

363

Files downloads

657