Games are an interesting field in computer science concerning the question whether a computer can learn the game strategies just from self-play, without explicitly programming the tactics or performing exhaustive search. This is a branch of artificial intelligence (AI).

Recently (January'2018), we have released Gameboard Hex in GBGGBG, the General Board Game playing and learning framework to the research community as another open-source project.

https://github.com/WolfgangKonen/GBG

GBG takes the abstraction one level higher in that it provides a software framework with standardized interfaces for arbitrary games and arbitrary AI agents. GBG helps students and researchers to take a quicker start-off into the area of game learning. Read more about GBG in the publications below.

Currently, the games implemented in GBG include 2048, Hex, Tic-Tac-Toe; more games are planned for the future. Current agents in GBG include MCTS, Max-N, Expectimax-N, TD-n-tuple and others.

The long-term goal of our research group is it to transfer these learning strategies to many other games (dots-and-boxes, go, Poker, checkers, Abalone, Sim, Othello, ...). The project is related to the research field known as General Game Playing (GGP). The aim of GGP and GBG is it to develop agents which are able to learn a great variety of games.

Read more about Games & Learning ...

Project themes in GBG for students (in German)

 

People

Wolfgang Konen, Markus Thill, Samineh Bagheri, Johannes Kutsch, Kevin Galitzki

 

Publications GBG

2018

Konen, Wolfgang

General Board Game Playing as Educational Tool for AI Competition and Learning Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) TH Köln - University of Applied Science, 2018, (submitted to IEEE Trans. on Games, preprint available at http://www.gm.fh-koeln.de/ciopwebpub/Kone18a.d/ToG-GBG.pdf).

Links | BibTeX

2017

Konen, Wolfgang

The GBG Class Interface Tutorial: General Board Game Playing and Learning Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) TH Köln - University of Applied Science, 2017, (e-print published at http://www.gm.fh-koeln.de/ciopwebpub/Kone17a.d/TR-GBG.pdf).

Links | BibTeX

Galitzki, Kevin

Selbstlernende Agenten für das skalierbare Spiel Hex: Untersuchung verschiedener KI-Verfahren im GBG-Framework Abschlussarbeit

TH Köln -- University of Applied Sciences, 2017, (Bachelor thesis).

Links | BibTeX

Kutsch, Johannes

KI-Agenten fur das Spiel 2048: Untersuchung von Lernalgorithmen für nichtdeterministische Spiele Abschlussarbeit

TH Köln -- University of Applied Sciences, 2017, (Bachelor thesis).

Links | BibTeX