Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations

Research on artificial development, reinforcement learning, and intrinsic motivations like curiosity could profit from the recently developed framework of multi-objective reinforcement learning. The combination of these ideas may lead to more realistic artificial models for life-long learning and go...

Descripción completa

Detalles Bibliográficos
Autores principales: Palm, Günther, Schwenker, Friedhelm
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Robotics and AI
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7805942/
https://www.ncbi.nlm.nih.gov/pubmed/33501023
http://dx.doi.org/10.3389/frobt.2019.00006
_version_ 1783636417991147520
author Palm, Günther
Schwenker, Friedhelm
author_facet Palm, Günther
Schwenker, Friedhelm
author_sort Palm, Günther
collection PubMed
description Research on artificial development, reinforcement learning, and intrinsic motivations like curiosity could profit from the recently developed framework of multi-objective reinforcement learning. The combination of these ideas may lead to more realistic artificial models for life-long learning and goal directed behavior in animals and humans.
format Online
Article
Text
id pubmed-7805942
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78059422021-01-25 Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations Palm, Günther Schwenker, Friedhelm Front Robot AI Robotics and AI Research on artificial development, reinforcement learning, and intrinsic motivations like curiosity could profit from the recently developed framework of multi-objective reinforcement learning. The combination of these ideas may lead to more realistic artificial models for life-long learning and goal directed behavior in animals and humans. Frontiers Media S.A. 2019-02-14 /pmc/articles/PMC7805942/ /pubmed/33501023 http://dx.doi.org/10.3389/frobt.2019.00006 Text en Copyright © 2019 Palm and Schwenker. 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 Robotics and AI
Palm, Günther
Schwenker, Friedhelm
Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations
title Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations
title_full Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations
title_fullStr Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations
title_full_unstemmed Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations
title_short Artificial Development by Reinforcement Learning Can Benefit From Multiple Motivations
title_sort artificial development by reinforcement learning can benefit from multiple motivations
topic Robotics and AI
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7805942/
https://www.ncbi.nlm.nih.gov/pubmed/33501023
http://dx.doi.org/10.3389/frobt.2019.00006
work_keys_str_mv AT palmgunther artificialdevelopmentbyreinforcementlearningcanbenefitfrommultiplemotivations
AT schwenkerfriedhelm artificialdevelopmentbyreinforcementlearningcanbenefitfrommultiplemotivations

Ejemplares similares