mdh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Reinforcement Learning in Keepaway Framework for RoboCup Simulation League
Mälardalens högskola, Akademin för innovation, design och teknik.
2011 (engelsk)Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
Abstract [en]

This thesis aims to apply the reinforcement learning into soccer robot and show the

great power of reinforcement learning for the RoboCup. In the first part, the

background of reinforcement learning is briefly introduced before showing the

previous work on it. Therefore the difficulty in implementing reinforcement learning

is proposed. The second section demonstrates basic concepts in reinforcement

learning, including three fundamental elements, state, action and reward respectively,

and three classical approaches, dynamic programming, monte carlo methods and

temporal-difference learning respectively. When it comes to keepaway framework,

more explanations are given to further combine keepaway with reinforcement

learning. After the suggestion about sarsa algorithm with two function approximation,

artificial neural network and tile coding, it is implemented successfully during the

simulations. The results show it significantly improves the performance of soccer

robot.

sted, utgiver, år, opplag, sider
2011. , s. 33
Emneord [en]
Reinforcement learning, Sarsa, Keepaway framework, Tile coding
HSV kategori
Identifikatorer
URN: urn:nbn:se:mdh:diva-13412OAI: oai:DiVA.org:mdh-13412DiVA, id: diva2:462781
Uppsök
Technology
Veileder
Tilgjengelig fra: 2011-12-08 Laget: 2011-12-08 Sist oppdatert: 2011-12-08bibliografisk kontrollert

Open Access i DiVA

fulltext(357 kB)218 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 357 kBChecksum SHA-512
571fe510d6dc91d47e33450c6b95f3e4ef5885f026ff2133ebe16693c20e70449fe5202fac119c2ce73447e352364679d789923437ff40eb288d2fa2ecd9e8cb
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 218 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 118 treff
RefereraExporteraLink to record
Permanent link

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