Section: New Results
Evaluation of intrinsic motivation systems as active learning
Developmental robots have a sharp need for mechanisms that may drive and self-organize the exploration of new skills, as well as identify and organize useful sub-spaces in its complex sensorimotor experiences. In psychology terms, this amount to trying to answer the question “What is interesting for a curious brain?”. Among the various trends of research which have approached this question, of particular interest is work on intrinsic motivation. Intrinsic motivations are mechanisms that guide curiosity-driven exploration, that were initially studied in psychology    and are now also being approached in neuroscience    . They have been proposed to be crucial for self-organizing developmental trajectories  as well as for guiding the learning of general and reusable skills (Barto et al., 2005). Experiments have been conducted in real-world robotic setups, such as in  where an intrinsic motivation system was shown to allow for the progressive discovery of skills of increasing complexity, such as reaching, biting and simple vocal imitation with and AIBO robot. In these experiments, the focus was on the study of how developmental stages could self-organize into a developmental trajectory without a direct pre-specification of these stages and their number. Yet, these algorithms can also be considered as “active learning” algorithms. This year, we have shown that some of them also allow for very efficient learning in the unprepared spaces with the typical properties of those encountered by developmental robots, outperforming standard active learning heuristics. These results were partly published in   .
Other publications are under preparation.