Intrinsically motivated goal exploration for active motor learning in robots: A case study

By Adrien Baranes, Pierre-Yves Oudeyer. 2010

113 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “…some of the basic ideas of IAC and RIAC architectures, combined with ideas from the SSA algorithm, into a multi-level active learning architecture called Self-Adaptive Goal Generation RIAC algorithm (SAGG-RIAC) (an outline and initial evaluation of this architecture was presented in [82]).”
Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning (2017, methodology): “…strands of research in robotics have presented algorithms that instantiate such intrinsically motivated goal exploration processes (Baranes and Oudeyer, 2010a; Rolf et al., 2010), using diﬀerent terminologies such as contextual policy search (Kupcsik et al., 2017; Queißer et al., 2016), or…”
The interaction of maturational constraints and intrinsic motivations in active motor development (2011, methodology): “…resolved by competence based intrinsic motivation mechanisms [11], [12], such as the Self-Adaptive Goal Generation Robust- Intelligent Adaptive Curiosity (SAGG-RIAC) algorithm which considers as interesting the local improvement of its competence to reach high-level self-generated goals [13].”
Socially guided intrinsic motivation for robot learning of motor skills (2013, background): “This system will also leverage efﬁcient techniques for active learning of inverse models using goal babbling (Baranes and Oudeyer 2013; Rolf et al. 2010; Baranes and Oudeyer 2010), but extend them with a technical integration with robot learning by demonstration techniques (Billard et al 2007).”
Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning? (2019, background): “Explore & Exploit is inspired by the hypothesis that goal-reaching is a good exploration strategy independent of hierarchy (Baranes & Oudeyer, 2010).”
Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints (2013, methodology): “Such an integration of maturation and intrinsic motivation is what has been explored in the McSAGG architecture, coupling SAGG-RIAC with maturational constraints (Baranes and Oudeyer, 2010b).”
Intrinsic Motivation and Reinforcement Learning (2013, background): “Further, theories relevant to intrinsic motivation have been proposed that are not based on RL, e.g., Andry et al. (2004), Baranes and Oudeyer (2010), Friston et al. (2010), Hesse et al. (2009).”
Intrinsically Motivated Learning in Natural and Artificial Systems (2013, background): “…the pervasive influence of brain reward systems on behavior (e.g., Linden 2011), other theoretical principles— not discussed here—have been proposed that can account for aspects of intrinsic motivation (e.g., Andry et al. 2004; Baranes and Oudeyer 2010; Friston et al. 2010; Hesse et al. 2009).”