Online Goal Babbling for rapid bootstrapping of inverse models in high dimensions

84 citations recorded by the source corpus.

How researchers see this paper

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

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, neutral): “� Possible problems happening due to singularities [105,109,110] beingbypassedbyaddingnoiseinthejointconfigurations(see[96] forastudyaboutthisproblem).”
GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning (2016, background): “The goal-babbling framework (Section I-B) has underlined the importance of goals in the optimisation of learning processes in high-dimensional action spaces involving redundant robot controllers [11], [68], shifting the exploration of the artificial agents from the motor-space to the task-space.”
Curiosity-driven phonetic learning (2012, background): “Additionally, it was shown in previous models that learning redundant inverse models could be achieved more efficiently if exploration was driven by goal babbling, triggering reaching, rather than driven by direct motor babbling [5], [16].”
The strategic student approach for life-long exploration and learning (2012, background): “a local inverse model (see also [44] and [45] for similar ideas).”