kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
A Comparative Study of Learning Algorithms in Imperfect-Information Games
KTH, School of Engineering Sciences (SCI).
2025 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

By their very nature, imperfect-information games pose challenges of uncertainty and deception. The development of Counterfactual Regret Minimization (CFR) and its later variant CFR+, has been essential to the success of current state-of-the-art poker bots, which now exceed human performance. In this report, we implement and apply CFR and CFR+ to One-Card Poker to examine their rate of convergence. We verify the well-known result that CFR+ converges faster than CFR in One-Card Poker. We further demonstrate that CFR+ attains lower exploitability than CFR at every iteration count tested.

Place, publisher, year, edition, pages
2025.
Series
TRITA-SCI-GRU ; 2025:261
National Category
Mathematical sciences
Identifiers
URN: urn:nbn:se:kth:diva-366678OAI: oai:DiVA.org:kth-366678DiVA, id: diva2:1982863
Subject / course
Mathematical Statistics
Educational program
Master of Science in Engineering - Engineering Mathematics
Supervisors
Examiners
Available from: 2025-07-09 Created: 2025-07-09 Last updated: 2025-07-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Engineering Sciences (SCI)
Mathematical sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 262 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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