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
Självlärande Hare and Hounds-spelare med Q-learning.
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2011 (Swedish)Independent thesis Advanced level (professional degree), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This report deals with reinforcement learning, a branch of machine learning. The report examines whether a Q-learning agent can learn to play the board game Hare and Hounds. By implementing the Q-learning algorithm, analysis has been completed on different aspects of the learning process. The experiments performed to examine the Q-learning is one test of the learning parameters, one test against a simple strategy and one test that shows the Q-learning convergence. The investigations show that Q-learning is well suited for learning to play the board game Hare and Hounds.

Abstract [sv]

Denna rapport behandlar belöningsbaserad inlärning, en gren inom maskininlärning. I rapporten undersöks huruvida en Q-learning agent kan lära sig att spela brädspelet Hare and Hounds. Genom att implementera Q-learning har analyser kunnat genomföras på olika aspekter av inlärningsprocessen. De experiment som genomförts för att undersöka Q-learning är ett test på inlärningsparametrarna, ett test mot en simpel spelstrategi samt ett test som visar Q-learnings konvergens. Undersökningarna visar att Q-learning lämpar sig väl för att lära sig spela Hare and Hounds.

Place, publisher, year, edition, pages
2011.
Series
Kandidatexjobb CSC, K11048
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-130825OAI: oai:DiVA.org:kth-130825DiVA: diva2:654272
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/hartwig_harald_OCH_westermark_max_K11048.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: 38 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