Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Self-learning Game Player – Connect-4 with Q-learning.
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2011 (English)Independent thesis Advanced level (professional degree), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

The microprocessors emerged in the beginning of the 70s; with them the computers got greater capacity to process huge numbers of data. This was of great help to the software engineers who worked in the artificial intelligence AI field, with machine learning as a central part to AI research. Our main task is to develop a simple board game of connect-4 then implement a self learning game player Agent using reinforcement learning. This report will include the methods that will be implemented on the Agent and the following results after a large amount of games have been executed.

Abstract [sv]

Datorerna fick bättre kapacitet att hantera stora mängder data när Intel introducerade mikroprocessorerna på marknaden I början av 70-talet. Det var till stor hjälp för ingenjörerna inom mjukvara utveckling som arbetade med artificiell intelligens AI. Ett delområde inom AI är maskininlärning d.v.s. algoritmer som lär sig genom erfarenhet. Vårt mål är att utveckla ett simpelt brädspel av fyra i rad och implementera en algoritm som ska lära sig spelet utan instruktioner om hur den ska agera. Algoritmen lär sig själv genom att få belöningar för lyckade omgångar och då minnas hur den gick tillväga för att lyckas när den stöter på samma scenario igen. Den här rapporten beskriver de metoder som kommer att implementeras på vår algoritm samt resultaten som uppnås.

Place, publisher, year, edition, pages
2011.
Series
Kandidatexjobb CSC, K11064
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-130832OAI: oai:DiVA.org:kth-130832DiVA: diva2:654279
Educational program
Master of Science in Engineering - Computer Science and Technology
Uppsok
Technology
Supervisors
Examiners
Available from: 2013-10-07 Created: 2013-10-07

Open Access in DiVA

No full text

Other links

http://www.csc.kth.se/utbildning/kandidatexjobb/datateknik/2011/rapport/jakobsson_tonie_OCH_persson_john_K11064.pdf
By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 59 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf