The interaction of maturational constraints and intrinsic motivations in active motor development

By Adrien Baranes, Pierre-Yves Oudeyer. 2011

29 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Cognitive Neuroscience

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 Biomedical Engineering

In Cognitive Neuroscience

Citations in the corpus

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “Using such constraints in synergy with goal babbling and intrinsic motivation, such as explored in [129], would potentially allow to constrain and simplify further learning since the first actions of the robot [130,131], and could be crucial when considering life-long learning in unbounded task…”
Automatic Curriculum Learning For Deep RL: A Short Survey (2020, methodology): “The idea of changing the properties of the agent (here its memory) was also studied in developmental robotics [Baranes and Oudeyer, 2011], policy distillation methods [Czarnecki et al.”
The strategic student approach for life-long exploration and learning (2012, background): “A second family of approaches have considered internal mechanisms of maturation, which control the evolution of the complexity of percepts and actions by progressively increasing the number or spatio-temporal resolution of motor channels [4], [5] or sensori channels [5]–[7].”
Towards Deep Developmental Learning (2016, background): “Furthermore, the dynamics of this complexity growth should be partly conditioned by maturational constraints related to the biological growth of the agent, as put forward in [153], [151].”
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning (2018, unknown): “al space is of unknown size [1]. It was also shown to be robust to degradation in learning performances due to continual changes in the environment structure, e.g. when the agent body grows with time [13]. Another line of work called learning with auxiliary tasks implements multi-task learning and c”
Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints (2013, unknown): “…competence value inside R i , hence the local competence progress, over a sliding time window of the ζ more recent goals attempted inside R i (see Baranes and Oudeyer, 2011 for a justification of the absolute value): interest(R i ) =   |Ri|− ζ 2 j=|Ri|−ζ γ s j   −   |Ri| j=|Ri|− ζ 2 γ s…”