Relational reinforcement learning for planning with exogenous effects

Probabilistic planners have improved recently to the point that they can solve difficult tasks with complex and expressive models. In contrast, learners cannot tackle yet the expressive models that planners do, which forces complex models to be mostly handcrafted. We propose a new learning approach...

ver descrição completa

Detalhes bibliográficos
Autores: Martinez Martinez, David, Alenyà Ribas, Guillem|||0000-0002-6018-154X, Ribeiro, Tony, Inoue, Katsumi, Torras, Carme|||0000-0002-2933-398X
Formato: artículo
Fecha de publicación:2017
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/113085
Acesso em linha:https://hdl.handle.net/2117/113085
Access Level:acceso abierto
Palavra-chave:Learning Models for Planning
Model-Based RL
Probabilistic Planning
Active Learning
Robot Learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
id ES_e1dbfebd645f3c1dced7a6859320e4f2
oai_identifier_str oai:upcommons.upc.edu:2117/113085
network_acronym_str ES
network_name_str España
repository_id_str
spelling Relational reinforcement learning for planning with exogenous effectsMartinez Martinez, DavidAlenyà Ribas, Guillem|||0000-0002-6018-154XRibeiro, TonyInoue, KatsumiTorras, Carme|||0000-0002-2933-398XLearning Models for PlanningModel-Based RLProbabilistic PlanningActive LearningRobot LearningClassificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)Àrees temàtiques de la UPC::Informàtica::RobòticaProbabilistic planners have improved recently to the point that they can solve difficult tasks with complex and expressive models. In contrast, learners cannot tackle yet the expressive models that planners do, which forces complex models to be mostly handcrafted. We propose a new learning approach that can learn relational probabilistic models with both action effects and exogenous effects. The proposed learning approach combines a multi-valued variant of inductive logic programming for the generation of candidate models, with an optimization method to select the best set of planning operators to model a problem. We also show how to combine this learner with reinforcement learning algorithms to solve complete problems. Finally, experimental validation is provided that shows improvements over previous work in both simulation and a robotic task. The robotic task involves a dynamic scenario with several agents where a manipulator robot has to clear the tableware on a table. We show that the exogenous effects learned by our approach allowed the robot to clear the table in a more efficient way.Peer Reviewed20172017-01-0120182018-01-22journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/113085reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen 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:2117/1130852026-05-27T15:37:01Z
dc.title.none.fl_str_mv Relational reinforcement learning for planning with exogenous effects
title Relational reinforcement learning for planning with exogenous effects
spellingShingle Relational reinforcement learning for planning with exogenous effects
Martinez Martinez, David
Learning Models for Planning
Model-Based RL
Probabilistic Planning
Active Learning
Robot Learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
title_short Relational reinforcement learning for planning with exogenous effects
title_full Relational reinforcement learning for planning with exogenous effects
title_fullStr Relational reinforcement learning for planning with exogenous effects
title_full_unstemmed Relational reinforcement learning for planning with exogenous effects
title_sort Relational reinforcement learning for planning with exogenous effects
dc.creator.none.fl_str_mv Martinez Martinez, David
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Ribeiro, Tony
Inoue, Katsumi
Torras, Carme|||0000-0002-2933-398X
author Martinez Martinez, David
author_facet Martinez Martinez, David
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Ribeiro, Tony
Inoue, Katsumi
Torras, Carme|||0000-0002-2933-398X
author_role author
author2 Alenyà Ribas, Guillem|||0000-0002-6018-154X
Ribeiro, Tony
Inoue, Katsumi
Torras, Carme|||0000-0002-2933-398X
author2_role author
author
author
author
dc.subject.none.fl_str_mv Learning Models for Planning
Model-Based RL
Probabilistic Planning
Active Learning
Robot Learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
topic Learning Models for Planning
Model-Based RL
Probabilistic Planning
Active Learning
Robot Learning
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
description Probabilistic planners have improved recently to the point that they can solve difficult tasks with complex and expressive models. In contrast, learners cannot tackle yet the expressive models that planners do, which forces complex models to be mostly handcrafted. We propose a new learning approach that can learn relational probabilistic models with both action effects and exogenous effects. The proposed learning approach combines a multi-valued variant of inductive logic programming for the generation of candidate models, with an optimization method to select the best set of planning operators to model a problem. We also show how to combine this learner with reinforcement learning algorithms to solve complete problems. Finally, experimental validation is provided that shows improvements over previous work in both simulation and a robotic task. The robotic task involves a dynamic scenario with several agents where a manipulator robot has to clear the tableware on a table. We show that the exogenous effects learned by our approach allowed the robot to clear the table in a more efficient way.
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
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/113085
url https://hdl.handle.net/2117/113085
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
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_ 1869422332558180352
score 15.228081

Registos relacionados