Cargando…

An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning

We propose an architecture for the open-ended learning and control of embodied agents. The architecture learns action affordances and forward models based on intrinsic motivations and can later use the acquired knowledge to solve extrinsic tasks by decomposing them into sub-tasks, each solved with o...

Descripción completa

Detalles Bibliográficos
Autores principales: Baldassarre, Gianluca, Lord, William, Granato, Giovanni, Santucci, Vieri Giuliano
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6676802/
https://www.ncbi.nlm.nih.gov/pubmed/31402859
http://dx.doi.org/10.3389/fnbot.2019.00045
_version_ 1783440831803293696
author Baldassarre, Gianluca
Lord, William
Granato, Giovanni
Santucci, Vieri Giuliano
author_facet Baldassarre, Gianluca
Lord, William
Granato, Giovanni
Santucci, Vieri Giuliano
author_sort Baldassarre, Gianluca
collection PubMed
description We propose an architecture for the open-ended learning and control of embodied agents. The architecture learns action affordances and forward models based on intrinsic motivations and can later use the acquired knowledge to solve extrinsic tasks by decomposing them into sub-tasks, each solved with one-step planning. An affordance is here operationalized as the agent's estimate of the probability of success of an action performed on a given object. The focus of the work is on the overall architecture while single sensorimotor components are simplified. A key element of the architecture is the use of “active vision” that plays two functions, namely to focus on single objects and to factorize visual information into the object appearance and object position. These processes serve both the acquisition and use of object-related affordances, and the decomposition of extrinsic goals (tasks) into multiple sub-goals (sub-tasks). The architecture gives novel contributions on three problems: (a) the learning of affordances based on intrinsic motivations; (b) the use of active vision to decompose complex extrinsic tasks; (c) the possible role of affordances within planning systems endowed with models of the world. The architecture is tested in a simulated stylized 2D scenario in which objects need to be moved or “manipulated” in order to accomplish new desired overall configurations of the objects (extrinsic goals). The results show the utility of using intrinsic motivations to support affordance learning; the utility of active vision to solve composite tasks; and the possible utility of affordances for solving utility-based planning problems.
format Online
Article
Text
id pubmed-6676802
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-66768022019-08-09 An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning Baldassarre, Gianluca Lord, William Granato, Giovanni Santucci, Vieri Giuliano Front Neurorobot Neuroscience We propose an architecture for the open-ended learning and control of embodied agents. The architecture learns action affordances and forward models based on intrinsic motivations and can later use the acquired knowledge to solve extrinsic tasks by decomposing them into sub-tasks, each solved with one-step planning. An affordance is here operationalized as the agent's estimate of the probability of success of an action performed on a given object. The focus of the work is on the overall architecture while single sensorimotor components are simplified. A key element of the architecture is the use of “active vision” that plays two functions, namely to focus on single objects and to factorize visual information into the object appearance and object position. These processes serve both the acquisition and use of object-related affordances, and the decomposition of extrinsic goals (tasks) into multiple sub-goals (sub-tasks). The architecture gives novel contributions on three problems: (a) the learning of affordances based on intrinsic motivations; (b) the use of active vision to decompose complex extrinsic tasks; (c) the possible role of affordances within planning systems endowed with models of the world. The architecture is tested in a simulated stylized 2D scenario in which objects need to be moved or “manipulated” in order to accomplish new desired overall configurations of the objects (extrinsic goals). The results show the utility of using intrinsic motivations to support affordance learning; the utility of active vision to solve composite tasks; and the possible utility of affordances for solving utility-based planning problems. Frontiers Media S.A. 2019-07-26 /pmc/articles/PMC6676802/ /pubmed/31402859 http://dx.doi.org/10.3389/fnbot.2019.00045 Text en Copyright © 2019 Baldassarre, Lord, Granato and Santucci. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Baldassarre, Gianluca
Lord, William
Granato, Giovanni
Santucci, Vieri Giuliano
An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning
title An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning
title_full An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning
title_fullStr An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning
title_full_unstemmed An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning
title_short An Embodied Agent Learning Affordances With Intrinsic Motivations and Solving Extrinsic Tasks With Attention and One-Step Planning
title_sort embodied agent learning affordances with intrinsic motivations and solving extrinsic tasks with attention and one-step planning
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6676802/
https://www.ncbi.nlm.nih.gov/pubmed/31402859
http://dx.doi.org/10.3389/fnbot.2019.00045
work_keys_str_mv AT baldassarregianluca anembodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT lordwilliam anembodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT granatogiovanni anembodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT santuccivierigiuliano anembodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT baldassarregianluca embodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT lordwilliam embodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT granatogiovanni embodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning
AT santuccivierigiuliano embodiedagentlearningaffordanceswithintrinsicmotivationsandsolvingextrinsictaskswithattentionandonestepplanning