Intrinsically Motivated Learning of Real-World Sensorimotor Skills with Developmental Constraints

By Pierre-Yves Oudeyer, Adrien Baranes, Frederic Kaplan. 2013

78 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, 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 Biomedical Engineering

In Control and Systems Engineering

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “Then an essential question is: which experiments should C conduct to quickly improve M? The Formal Theory of Fun and Creativity (Schmidhuber, 2006a, 2013b) formalizes driving forces and value functions behind such curious and exploratory behavior: A measure of the learning progress of M becomes the ”
PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable Problem (2011, background): “3; compare [1, 5, 22, 20]), P OWERPLAY provably (by design) does not have any problems with online learning—it cannot forget previously learned skills, auto matically segmenting its life into a sequence of clearly identified tasks with explicitly recorded solution s.”
First Experiments with PowerPlay (2012, background): “tinually grows based on which task is easy to invent and validate, given what is already known. Unlike our ﬁrst implementations of curious / creative / playful agents from the 1990s [17, 29, 18] (cf. [1, 4, 13, 11]), POWERPLAY provably (by design) does not have any problems with online learning—it c”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, background): “They seem to get intrinsic reward for creating experiments leading to observations that obey a previously unknown law that allows for better compression of the observations—corresponding to the discovery of a temporarily interesting, subjectively novel regularity [224, 239, 241] (compare also [261, ”
Socially guided intrinsic motivation for robot learning of motor skills (2013, background): “In particular, they address only partially the challenges of unlearn-ability and unboundedness (Oudeyer et al. 2013), which rises with the use of real high-dimensional bodies with continuous sensorimotor channels and an open-ended environment.”
Intrinsically Motivated Learning in Natural and Artificial Systems (2013, background): “robotics (Hart and Grupen 2012; Natale et al. 2012; Nehmzow et al. 2012; Oudeyer et al. 2012), machine learning (Barto 2012; Schmidhuber 2012), computational modelling (Baldassarre and Mirolli 2012; Dayan 2012; Gurney et al.”