Fulltext available Open Access
DC FieldValueLanguage
dc.contributor.advisorMeisel, Andreas-
dc.contributor.authorRohden, Andre
dc.date.accessioned2020-09-29T15:01:11Z-
dc.date.available2020-09-29T15:01:11Z-
dc.date.created2019
dc.date.issued2019-04-17
dc.identifier.urihttp://hdl.handle.net/20.500.12738/8674-
dc.description.abstractReinforcement Learning ermöglicht einem selbstlernenden Agenten ein unbemanntes Flugobjekt in unkontrollierten Flugzuständen zu stabilisieren. Um dies zu erreichen, wird ein Deep Deterministic Policy Gradient Algorithmus angewendet. Durch Erweiterung wie Experience Replay Speicher, parametrisiertem Rauschen, Prioritized Experience Replay, Hindsight Experience Replay und Curriculum Learning lassen sich darüberhinaus Umgegebung mit sparse Reward trainieren.de
dc.description.abstractReinforcement learning allows a self-learning agent to stabilize an unmanned aerial vehicle in uncontrolled flight states. To achieve this, a deep deterministic policy gradient algorithm is applied. Through extensions like experience replay memory, parameterized noise, prioritized experience replay, hindsight experience replay and curriculum learning, it is furthermore possible to train environments with sparse reward.en
dc.language.isodede
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/-
dc.subjectreinforcement learningen
dc.subjectdeep deterministic policy gradienten
dc.subjectexperience replay memoryen
dc.subjectcurriculum learningen
dc.subjectquadcopteren
dc.subject.ddc004 Informatik
dc.titleStabilisierung unkontrollierter Flugzustände mit Reinforcement Learningde
dc.title.alternativeStabilization of uncontrolled flight states with reinforcement learningen
dc.typeThesis
openaire.rightsinfo:eu-repo/semantics/openAccess
thesis.grantor.departmentDepartment Informatik
thesis.grantor.placeHamburg
thesis.grantor.universityOrInstitutionHochschule für angewandte Wissenschaften Hamburg
tuhh.contributor.refereeFohl, Wolfgang-
tuhh.gvk.ppn1663355266
tuhh.identifier.urnurn:nbn:de:gbv:18302-reposit-86762-
tuhh.note.intern1
tuhh.oai.showtrueen_US
tuhh.opus.id4675
tuhh.publication.instituteDepartment Informatik
tuhh.type.opusMasterarbeit-
dc.subject.gndOperante Konditionierung
dc.type.casraiSupervised Student Publication-
dc.type.dinimasterThesis-
dc.type.drivermasterThesis-
dc.type.statusinfo:eu-repo/semantics/publishedVersion
dc.type.thesismasterThesis
dcterms.DCMITypeText-
tuhh.dnb.statusdomain-
item.advisorGNDMeisel, Andreas-
item.languageiso639-1de-
item.fulltextWith Fulltext-
item.creatorGNDRohden, Andre-
item.openairetypeThesis-
item.grantfulltextopen-
item.creatorOrcidRohden, Andre-
item.cerifentitytypePublications-
item.openairecristypehttp://purl.org/coar/resource_type/c_46ec-
Appears in Collections:Theses
Files in This Item:
File Description SizeFormat
masterthesis_rohden.pdf18.29 MBAdobe PDFView/Open
Show simple item record

Page view(s)

139
checked on Jan 13, 2025

Download(s)

192
checked on Jan 13, 2025

Google ScholarTM

Check

HAW Katalog

Check

Note about this record


Items in REPOSIT are protected by copyright, with all rights reserved, unless otherwise indicated.