Intrinsic motivations are mechanisms that guide curiosity-driven exploration (Berlyne, 1965). They have been proposed to be crucial for self-organizing developmental trajectories (Oudeyer et al. , 2007) as well as for guiding the learning of general and reusable skills (Barto et al., 2005). Here, we argue that they can be considered as “active learning” algorithms, and show that some of them also allow for very efficient learning in unprepared sensorimotor spaces, outperforming existing active learning algorithms.