Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Utilizing state-of-art NeuroES and GPGPU to optimize Mario AI
Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, Institutionen för kreativa teknologier.
2014 (Engelska)Studentuppsats (Examensarbete)
Abstract [en]

Context. Reinforcement Learning (RL) is a time consuming effort that requires a lot of computational power as well. There are mainly two approaches to improving RL efficiency, the theoretical mathematics and algorithmic approach or the practical implementation approach. In this study, the approaches are combined in an attempt to reduce time consumption.\newline Objectives. We investigate whether modern hardware and software, GPGPU, combined with state-of-art Evolution Strategies, CMA-Neuro-ES, can potentially increase the efficiency of solving RL problems.\newline Methods. In order to do this, both an implementational as well as an experimental research method is used. The implementational research mainly involves developing and setting up an experimental framework in which to measure efficiency through benchmarking. In this framework, the GPGPU/ES solution is later developed. Using this framework, experiments are conducted on a conventional sequential solution as well as our own parallel GPGPU solution.\newline Results. The results indicate that utilizing GPGPU and state-of-art ES when attempting to solve RL problems can be more efficient in terms of time consumption in comparison to a conventional and sequential CPU approach.\newline Conclusions. We conclude that our proposed solution requires additional work and research but that it shows promise already in this initial study. As the study is focused on primarily generating benchmark performance data from the experiments, the study lacks data on RL efficiency and thus motivation for using our approach. However we do conclude that the GPGPU approach suggested does allow less time consuming RL problem solving.

Ort, förlag, år, upplaga, sidor
2014. , s. 62
Nyckelord [en]
Reinforcement Learning, Evolution Strategies, GPGPU, Artifical Neural Networks
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:bth-4386Lokalt ID: oai:bth.se:arkivexCD300C9EED8B0F11C1257D0400405635OAI: oai:DiVA.org:bth-4386DiVA, id: diva2:831724
Utbildningsprogram
PAACI Civilingenjör i spel- och programvaruteknik
Uppsök
teknik
Handledare
Tillgänglig från: 2015-04-22 Skapad: 2014-06-27 Senast uppdaterad: 2018-01-11Bibliografiskt granskad

Open Access i DiVA

fulltext(1605 kB)248 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 1605 kBChecksumma SHA-512
ff61c9b0f6739efc5c612e4be8bdc75d08a0ae7762ee5206700514fd16ca2a1e097272c1de9013b6ddf5d8683a22f996796e94af59cf56f2b55baea1f97e94f6
Typ fulltextMimetyp application/pdf

Av organisationen
Institutionen för kreativa teknologier
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 248 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 203 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf