Relational reinforcement learning with guided demonstrations

© <year>. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0

Detalles Bibliográficos
Autores: Martínez Martínez, David, Alenyà Ribas, Guillem|||0000-0002-6018-154X, Torras, Carme|||0000-0002-2933-398X
Tipo de recurso: artículo
Fecha de publicación:2017
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/113084
Acceso en línea:https://hdl.handle.net/2117/113084
https://dx.doi.org/10.1016/j.artint.2015.02.006
Access Level:acceso abierto
Palabra clave:generalisation (artificial intelligence)
learning (artificial intelligence)
manipulators
uncertainty handling
human-robot interaction
model-based reinforcement learning
active learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
id ES_c9c1dbfc1e5bcefdbc65dea88be5a9b2
oai_identifier_str oai:upcommons.upc.edu:2117/113084
network_acronym_str ES
network_name_str España
repository_id_str
spelling Relational reinforcement learning with guided demonstrationsMartínez Martínez, DavidAlenyà Ribas, Guillem|||0000-0002-6018-154XTorras, Carme|||0000-0002-2933-398Xgeneralisation (artificial intelligence)learning (artificial intelligence)manipulatorsuncertainty handlinghuman-robot interactionmodel-based reinforcement learningactive learningClassificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)Àrees temàtiques de la UPC::Informàtica::Robòtica© <year>. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0Model-based reinforcement learning is a powerful paradigm for learning tasks in robotics. However, in-depth exploration is usually required and the actions have to be known in advance. Thus, we propose a novel algorithm that integrates the option of requesting teacher demonstrations to learn new domains with fewer action executions and no previous knowledge. Demonstrations allow new actions to be learned and they greatly reduce the amount of exploration required, but they are only requested when they are expected to yield a significant improvement because the teacher's time is considered to be more valuable than the robot's time. Moreover, selecting the appropriate action to demonstrate is not an easy task, and thus some guidance is provided to the teacher. The rule-based model is analyzed to determine the parts of the state that may be incomplete, and to provide the teacher with a set of possible problems for which a demonstration is needed. Rule analysis is also used to find better alternative models and to complete subgoals before requesting help, thereby minimizing the number of requested demonstrations. These improvements were demonstrated in a set of experiments, which included domains from the international planning competition and a robotic task. Adding teacher demonstrations and rule analysis reduced the amount of exploration required by up to 60% in some domains, and improved the success ratio by 35% in other domainsPeer Reviewed20172017-01-0120182018-01-22journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/113084https://dx.doi.org/10.1016/j.artint.2015.02.006reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengEuropean Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 269959 Intelligent observation and execution of Actions and manipulationsopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivs 3.0 Spainhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/1130842026-05-27T15:37:01Z
dc.title.none.fl_str_mv Relational reinforcement learning with guided demonstrations
title Relational reinforcement learning with guided demonstrations
spellingShingle Relational reinforcement learning with guided demonstrations
Martínez Martínez, David
generalisation (artificial intelligence)
learning (artificial intelligence)
manipulators
uncertainty handling
human-robot interaction
model-based reinforcement learning
active learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
title_short Relational reinforcement learning with guided demonstrations
title_full Relational reinforcement learning with guided demonstrations
title_fullStr Relational reinforcement learning with guided demonstrations
title_full_unstemmed Relational reinforcement learning with guided demonstrations
title_sort Relational reinforcement learning with guided demonstrations
dc.creator.none.fl_str_mv Martínez Martínez, David
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Torras, Carme|||0000-0002-2933-398X
author Martínez Martínez, David
author_facet Martínez Martínez, David
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Torras, Carme|||0000-0002-2933-398X
author_role author
author2 Alenyà Ribas, Guillem|||0000-0002-6018-154X
Torras, Carme|||0000-0002-2933-398X
author2_role author
author
dc.subject.none.fl_str_mv generalisation (artificial intelligence)
learning (artificial intelligence)
manipulators
uncertainty handling
human-robot interaction
model-based reinforcement learning
active learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
topic generalisation (artificial intelligence)
learning (artificial intelligence)
manipulators
uncertainty handling
human-robot interaction
model-based reinforcement learning
active learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
description © <year>. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0
publishDate 2017
dc.date.none.fl_str_mv 2017
2017-01-01
2018
2018-01-22
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/113084
https://dx.doi.org/10.1016/j.artint.2015.02.006
url https://hdl.handle.net/2117/113084
https://dx.doi.org/10.1016/j.artint.2015.02.006
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://dx.doi.org/10.13039/100011102 Seventh Framework Programme 269959 Intelligent observation and execution of Actions and manipulations
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419398518800384
score 15.300719

Similares en LA Referencia