+++ Update 08/2023: FutureWorkGBG: Project themes in GBG for students (PDF) +++

 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).

In January'2018 we 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 (than in the previous Connect-4 project) 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, Othello, Sim, Nim, 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, ...). 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 ...

FutureWorkGBG: Project themes in GBG for students (PDF)

 

Contributors

Wolfgang Konen, Markus Thill, Samineh Bagheri, Johannes Kutsch, Kevin Galitzki, Felix Barsnick, Yannick Dittmar, Julian Cöln, Johannes Scheiermann

Publications GBG

The article General Board Game Playing for Education and Research in Generic AI Game Learning (2019) provides a scientific overview on GBG. The technical report The GBG Class Interface Tutorial V2.3: General Board Game Playing and Learning (Sep 2022) gives an introduction to GBG more from the programmer's perspective.

2023

Konen, Wolfgang

Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning Artikel

In: arXiv preprint arXiv:2301.12167, 2023.

Links | BibTeX

Seven, Meltem

KI-Agenten im Vergleich: Erfolg von Agenten des Ludii General Game Systems in Partien gegen perfekte oder starke Agenten am Beispiel der Spiele Vier Gewinnt, Nim und Othello Abschlussarbeit

TH Köln – University of Applied Sciences, 2023, (Bachelor thesis).

Links | BibTeX

2022

Konen, Wolfgang

The GBG Class Interface Tutorial V2.3: General Board Game Playing and Learning Forschungsbericht

TH Köln 2022.

Links | BibTeX

Cöln, Julian

KI-Konzepte für das Erlernen nicht-deterministischer Spiele am Beispiel von "EinStein würfelt nicht!" Abschlussarbeit

TH Köln – University of Applied Sciences, 2022, (Bachelor thesis).

Links | BibTeX

Scheiermann, Johannes; Konen, Wolfgang

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time Artikel

In: arXiv preprint arXiv:2204.13307, 2022, (Preprint of the IEEE ToG 2022 paper).

Links | BibTeX

Scheiermann, Johannes; Konen, Wolfgang

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time Artikel

In: IEEE Transactions on Games, 2022.

Links | BibTeX

2021

Meissner, Simon

Untersuchung des Spiel- und Lernerfolgs künstlicher Intelligenzen für ein nichtdeterministisches Spiel mit imperfekten Informationen: Blackjack in der Game-Learning-Umgebung ’General Board Game’ (GBG) Abschlussarbeit

TH Köln – University of Applied Sciences, 2021, (Bachelor thesis).

Links | BibTeX

Zeh, Tim

Untersuchung von allgemeinen KI-Agenten für das Spiel Poker im General Board Games Framework Abschlussarbeit

TH Köln – University of Applied Sciences, 2021, (Master thesis).

Links | BibTeX

Konen, Wolfgang; Bagheri, Samineh

Final adaptation reinforcement learning for N-player games Artikel

In: arXiv preprint arXiv:2111.14375, 2021.

Links | BibTeX

2020

Scheiermann, Johannes

Sind (trainierte) General-Purpose-RL-Agenten im Brettspiel Othello stärker als (untrainierte) General-Game-Playing Agenten? Forschungsbericht

TH Köln, Institut für Informatik 2020, (Praxisprojekt).

Links | BibTeX

Scheiermann, Johannes

AlphaZero-inspirierte KI-Agenten im General Board Game Playing Abschlussarbeit

TH Köln -- University of Applied Sciences, 2020, (Bachelor thesis).

Links | BibTeX

Konen, Wolfgang; Bagheri, Samineh

Reinforcement Learning for N-Player Games: The Importance of Final Adaptation Proceedings Article

In: Vasile, Bogdan Filipic Massimiliano (Hrsg.): 9th International Conference on Bioinspired Optimisation Methods and Their Applications (BIOMA), Bruxelles, 2020.

Links | BibTeX

Konen, Wolfgang; Bagheri, Samineh

Final Adaptation Reinforcement Learning for N-Player Games Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) 2020.

Links | BibTeX

Konen, Wolfgang

The GBG Class Interface Tutorial V2.2: General Board Game Playing and Learning Forschungsbericht

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) 2020.

Links | BibTeX

2019

Cöln, Julian; Dittmar, Yannick

Untersuchung von KI Agenten im Spiel Othello Forschungsbericht

TH Köln, Institut für Informatik 2019.

Links | BibTeX

Konen, Wolfgang

General Board Game Playing for Education and Research in Generic AI Game Learning Proceedings Article

In: Perez, Diego; Mostaghim, Sanaz; Lucas, Simon (Hrsg.): IEEE Conference on Games, London, 2019.

Links | BibTeX

Barsnick, Felix

Implementierung und Untersuchung eines Turniersystems für KI-Agenten in Brettspielen Abschlussarbeit

TH Köln -- University of Applied Sciences, 2019, (Master thesis).

Links | BibTeX

2017

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

2012

Thill, Markus; Koch, Patrick; Konen, Wolfgang

Reinforcement learning with n-tuples on the game Connect-4 Proceedings Article

In: Coello, Carlos A. Coello; Cutello, Vincenzo (Hrsg.): PPSN'2012: 12th International Conference on Parallel Problem Solving From Nature, Taormina, S. 184–194, Springer, Heidelberg, 2012.

Links | BibTeX