Learning to Trade in Strategic Board Games

Heriberto Cuayahuitl*, Simon Keizer, Oliver Lemon

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Automated agents in multiplayer board games often need to trade resources with their opponents-and trading strategically can lead to higher winning rates. While rule-based agents can be used for such a purpose, here we opt for a data-driven approach based on examples from human players for automatic trading in the game “Settlers of Catan”. Our experiments are based on data collected from human players trading in text-based Natural Language. We compare the performance of Bayesian Networks, Conditional Random Fields, and Random Forests in the task of ranking trading offers, and evaluate them both in an offline setting and online while playing the game against a rule-based baseline. Experimental results show that agents trained from data from average human players can outperform rule-based trading behavior, and that the Random Forest model achieves the best results.

Original languageEnglish
Title of host publicationComputer Games
PublisherSpringer
Pages83-95
Number of pages13
ISBN (Electronic)9783319394022
ISBN (Print)9783319394015
DOIs
Publication statusPublished - 2016

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer International Publishing
Volume614
ISSN (Print)1865-0929

ASJC Scopus subject areas

  • General Computer Science

Fingerprint

Dive into the research topics of 'Learning to Trade in Strategic Board Games'. Together they form a unique fingerprint.

Cite this