Data integration strategies for distributed reinforcement learning in robotics

The field of reinforcement learning, developed during the nineteen-eighties and nineties, is a branch of machine learning which has consistently shown wide potential. Using this theory, it is possible to design computer programs able to learn which actions must be taken, in a given environment, to m...

Full description

Bibliographic Details
Author: Salcedo Bosch, Martí
Format: master thesis
Publication Date:2020
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/185242
Online Access:https://hdl.handle.net/2117/185242
Access Level:Open access
Keyword:Neural networks (Computer science)
Robotics
Xarxes neuronals (Informàtica)
Robòtica
Àrees temàtiques de la UPC::Informàtica
id ES_de6bd9f0fa974c19b19f3ce1e3a115cf
oai_identifier_str oai:upcommons.upc.edu:2117/185242
network_acronym_str ES
network_name_str España
repository_id_str
spelling Data integration strategies for distributed reinforcement learning in roboticsDaten integrations strategien für verteiltes verstärkendes lernen in der robotikSalcedo Bosch, MartíNeural networks (Computer science)RoboticsXarxes neuronals (Informàtica)RobòticaÀrees temàtiques de la UPC::InformàticaThe field of reinforcement learning, developed during the nineteen-eighties and nineties, is a branch of machine learning which has consistently shown wide potential. Using this theory, it is possible to design computer programs able to learn which actions must be taken, in a given environment, to maximise a cumulative reward function. In other words, by rewarding the program, it is able to learn how to behave in order to solve a problem. Originally this field was mainly applied to discrete and finite environments, however, it was possible to handle continuous environments using traditional function approximators. Recently the field has experienced a revolution, with the increase of the computational capacity, which enabled the use of artificial neural networks as function approximators. It has shown surprising results previously thought unfeasible and the number of fields where it may be applied has drastically increased. Robotics is one of them and in the past few years the achieved results have been very promising. In general, and in robotics, one of the topics still to be deeply explored is the learning distribution. This distribution means to parallelise the learning, in other words, to have many workers facing the problem and sharing information instead of one isolated worker. With it, the learning can be optimised; involving shorter learning times and better knowledge of the environment among many other advantages. To contribute to this topic, in this project three different distributed architectures, based on the state-ofthe-art algorithms, will be designed and implemented. The learning will be distributed using many simulated robotic arms, that will work in parallel performing the same task.OutgoingUniversitat Politècnica de CatalunyaWunnik, Lucas Philippe vanWalter, FlorianWalter, Florian20202020-07-0120202020-04-27master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/185242reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/1852422026-05-27T15:37:01Z
dc.title.none.fl_str_mv Data integration strategies for distributed reinforcement learning in robotics
Daten integrations strategien für verteiltes verstärkendes lernen in der robotik
title Data integration strategies for distributed reinforcement learning in robotics
spellingShingle Data integration strategies for distributed reinforcement learning in robotics
Salcedo Bosch, Martí
Neural networks (Computer science)
Robotics
Xarxes neuronals (Informàtica)
Robòtica
Àrees temàtiques de la UPC::Informàtica
title_short Data integration strategies for distributed reinforcement learning in robotics
title_full Data integration strategies for distributed reinforcement learning in robotics
title_fullStr Data integration strategies for distributed reinforcement learning in robotics
title_full_unstemmed Data integration strategies for distributed reinforcement learning in robotics
title_sort Data integration strategies for distributed reinforcement learning in robotics
dc.creator.none.fl_str_mv Salcedo Bosch, Martí
author Salcedo Bosch, Martí
author_facet Salcedo Bosch, Martí
author_role author
dc.contributor.none.fl_str_mv Wunnik, Lucas Philippe van
Walter, Florian
Walter, Florian
dc.subject.none.fl_str_mv Neural networks (Computer science)
Robotics
Xarxes neuronals (Informàtica)
Robòtica
Àrees temàtiques de la UPC::Informàtica
topic Neural networks (Computer science)
Robotics
Xarxes neuronals (Informàtica)
Robòtica
Àrees temàtiques de la UPC::Informàtica
description The field of reinforcement learning, developed during the nineteen-eighties and nineties, is a branch of machine learning which has consistently shown wide potential. Using this theory, it is possible to design computer programs able to learn which actions must be taken, in a given environment, to maximise a cumulative reward function. In other words, by rewarding the program, it is able to learn how to behave in order to solve a problem. Originally this field was mainly applied to discrete and finite environments, however, it was possible to handle continuous environments using traditional function approximators. Recently the field has experienced a revolution, with the increase of the computational capacity, which enabled the use of artificial neural networks as function approximators. It has shown surprising results previously thought unfeasible and the number of fields where it may be applied has drastically increased. Robotics is one of them and in the past few years the achieved results have been very promising. In general, and in robotics, one of the topics still to be deeply explored is the learning distribution. This distribution means to parallelise the learning, in other words, to have many workers facing the problem and sharing information instead of one isolated worker. With it, the learning can be optimised; involving shorter learning times and better knowledge of the environment among many other advantages. To contribute to this topic, in this project three different distributed architectures, based on the state-ofthe-art algorithms, will be designed and implemented. The learning will be distributed using many simulated robotic arms, that will work in parallel performing the same task.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-07-01
2020
2020-04-27
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/185242
url https://hdl.handle.net/2117/185242
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
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
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
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_ 1869421972398538752
score 15,301603

Similar Items