Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking

This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/actio...

Descripción completa

Detalles Bibliográficos
Autores: El-Fakdi Sencianes, Andrés, Carreras Pérez, Marc
Tipo de recurso: artículo
Fecha de publicación:2008
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10256/2178
Acceso en línea:http://hdl.handle.net/10256/2178
Access Level:acceso abierto
Palabra clave:Aprenentatge per reforç
Robots autònoms
Autonomous robots
Reinforcement learning
id ES_b6e2c7dd070873351fc17d4161b341e6
oai_identifier_str oai:recercat.cat:10256/2178
network_acronym_str ES
network_name_str España
repository_id_str
spelling Policy gradient based Reinforcement Learning for real autonomous underwater cable trackingEl-Fakdi Sencianes, AndrésCarreras Pérez, MarcAprenentatge per reforçRobots autònomsAutonomous robotsReinforcement learningThis paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUVIEEE2008info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10256/2178http://hdl.handle.net/10256/2178© IEEE/RSJ International Conference on Intelligent Robots and Systems : 2008 : IROS 2008, 2008, p. 3635-3640Articles publicats (D-ATC)reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/semantics/altIdentifier/doi/10.1109/IROS.2008.4650873info:eu-repo/semantics/altIdentifier/isbn/978-1-4244-2057-5Tots els drets reservatsinfo:eu-repo/semantics/openAccessoai:recercat.cat:10256/21782026-05-29T05:05:01Z
dc.title.none.fl_str_mv Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
title Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
spellingShingle Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
El-Fakdi Sencianes, Andrés
Aprenentatge per reforç
Robots autònoms
Autonomous robots
Reinforcement learning
title_short Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
title_full Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
title_fullStr Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
title_full_unstemmed Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
title_sort Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
dc.creator.none.fl_str_mv El-Fakdi Sencianes, Andrés
Carreras Pérez, Marc
author El-Fakdi Sencianes, Andrés
author_facet El-Fakdi Sencianes, Andrés
Carreras Pérez, Marc
author_role author
author2 Carreras Pérez, Marc
author2_role author
dc.subject.none.fl_str_mv Aprenentatge per reforç
Robots autònoms
Autonomous robots
Reinforcement learning
topic Aprenentatge per reforç
Robots autònoms
Autonomous robots
Reinforcement learning
description This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV
publishDate 2008
dc.date.none.fl_str_mv 2008
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10256/2178
http://hdl.handle.net/10256/2178
url http://hdl.handle.net/10256/2178
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1109/IROS.2008.4650873
info:eu-repo/semantics/altIdentifier/isbn/978-1-4244-2057-5
dc.rights.none.fl_str_mv Tots els drets reservats
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Tots els drets reservats
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv © IEEE/RSJ International Conference on Intelligent Robots and Systems : 2008 : IROS 2008, 2008, p. 3635-3640
Articles publicats (D-ATC)
reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869417483754012672
score 15,811543

Similares en LA Referencia