Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner

We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interacti...

Full description

Bibliographic Details
Main Authors: Nguyen Sao Mai, Oudeyer Pierre-Yves
Format: Article
Language:English
Published: De Gruyter 2012-09-01
Series:Paladyn
Subjects:
Online Access:https://doi.org/10.2478/s13230-013-0110-z
_version_ 1827610201103007744
author Nguyen Sao Mai
Oudeyer Pierre-Yves
author_facet Nguyen Sao Mai
Oudeyer Pierre-Yves
author_sort Nguyen Sao Mai
collection DOAJ
description We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interactive learning and goal-babbling. It learns at the same time when, who and what to actively imitate from several available teachers, and learns when not to use social guidance but use active goal-oriented self-exploration. This is formalised in the framework of life-long strategic learning.
first_indexed 2024-03-09T07:45:35Z
format Article
id doaj.art-90314c72b169460683b7df1719673d26
institution Directory Open Access Journal
issn 2081-4836
language English
last_indexed 2024-03-09T07:45:35Z
publishDate 2012-09-01
publisher De Gruyter
record_format Article
series Paladyn
spelling doaj.art-90314c72b169460683b7df1719673d262023-12-03T03:18:30ZengDe GruyterPaladyn2081-48362012-09-013313614610.2478/s13230-013-0110-zActive Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation LearnerNguyen Sao Mai0Oudeyer Pierre-Yves1 Flowers Team, INRIA and ENSTA ParisTech, France, 200 avenue de la Vieille Tour, 33 405 Talence Cedex, France Flowers Team, INRIA and ENSTA ParisTech, France, 200 avenue de la Vieille Tour, 33 405 Talence Cedex, FranceWe present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interactive learning and goal-babbling. It learns at the same time when, who and what to actively imitate from several available teachers, and learns when not to use social guidance but use active goal-oriented self-exploration. This is formalised in the framework of life-long strategic learning.https://doi.org/10.2478/s13230-013-0110-zstrategic learnerimitation learningmimicryemulationartificial curiosityintrinsic motivationinteractive learneractive learninggoal babblingrobot skill learning
spellingShingle Nguyen Sao Mai
Oudeyer Pierre-Yves
Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner
Paladyn
strategic learner
imitation learning
mimicry
emulation
artificial curiosity
intrinsic motivation
interactive learner
active learning
goal babbling
robot skill learning
title Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner
title_full Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner
title_fullStr Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner
title_full_unstemmed Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner
title_short Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation Learner
title_sort active choice of teachers learning strategies and goals for a socially guided intrinsic motivation learner
topic strategic learner
imitation learning
mimicry
emulation
artificial curiosity
intrinsic motivation
interactive learner
active learning
goal babbling
robot skill learning
url https://doi.org/10.2478/s13230-013-0110-z
work_keys_str_mv AT nguyensaomai activechoiceofteacherslearningstrategiesandgoalsforasociallyguidedintrinsicmotivationlearner
AT oudeyerpierreyves activechoiceofteacherslearningstrategiesandgoalsforasociallyguidedintrinsicmotivationlearner