Connect-4 Game Playing Framework (C4GPF)c4board

Download C4GPF from GitHub

Connect-4 (Connect-Four) is an interesting game for several reasons. It is a non-trivial game, most humans will have difficulties to play well against a master level player (human or computer). At the same time it is of medium complexity (4.5·1012 states). It can be solved by tree-based methods (minimax, alpha-beta pruning).

Over the last years we have worked on a Java-based Connect-4 framework which makes it easily to develop, test and play with trainable Connect-4 agents. This work is now ready to be shared with other interested researchers or game-playing users. You can download it for your own research from this GitHub link.

"Why another Connect-4 program?", you might ask. There are many Connect-4 realizations, but – at least to our knowledge – no other one which incorporates a fast-playing perfect player. This player can be used to benchmark the strength of other, self-trained agents. We derived a variety of trainable agents (more details in our recent TCIAIG-paper "Online Adaptable Learning Rates for the Game Connect-4"). We have developed the framework in such a way that it is for an experienced Java programmer fairly easy to add his / her own agent. Once added, several methods for evaluation are at the disposal of the user.

So we want to encourage with this Connect-4 framework other researchers to benchmark their game-playing agents against other Connect-4 agents with well-known strength. If you are interested in having your Connect-4 agent being added to the C4GPF framework, feel free to contact us via eMail.

Features of C4GPF:

  • built-in reinforcement learning agent (TD-learning)
  • eligibility traces
  • several adaptive step-size learning schemes: TCL, IDBD, …
  • N-tuple features
  • perfect-playing Minimax agent with alpha-beta pruning and opening book
  • interface "Agent.java" for easy plug-in of new agents
  • several benchmarking options (competitions, move inspections, …)

Getting started:

  • Read the file CFour/READM.txt on GitHub
  • Read the file CFour/src/doc/index.htm = CFour/src/doc/Help.pdf (help file for the GUI of C4GPF)

Authors of C4GPF:

  • Markus Thill (markus.thill "at" fh-koeln.de)
  • Wolfgang Konen (wolfgang.konen "at" fh-koeln.de)

Download C4GPF from GitHub


Publications Games

2018

Konen, Wolfgang

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

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

Kutsch, Johannes

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

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

Links | BibTeX

Galitzki, Kevin

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

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

Links | BibTeX

Konen, Wolfgang

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

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

Links | BibTeX

2016

Bagheri, Samineh; Thill, Markus; Koch, Patrick; Konen, Wolfgang

Online Adaptable Learning Rates for the Game Connect-4 Journal Article

IEEE Transactions on Computational Intelligence and AI in Games, 8 (1), pp. 33-42, 2016, (accepted 11/2014).

Links | BibTeX

2015

Konen, Wolfgang

Reinforcement Learning for Board Games: The Temporal Difference Algorithm Technical Report

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Sciences, 2015.

Links | BibTeX

Konen, Wolfgang

Reinforcement Learning für Brettspiele: Der Temporal Difference Algorithmus Technical Report

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, 2015, (Updated version 2015).

Links | BibTeX

2014

Thill, Markus; Konen, Wolfgang

Connect-4 Game Playing Framework (C4GPF) Miscellaneous

2014.

Links | BibTeX

Konen, Wolfgang; Koch, Patrick

Adaptation in Nonlinear Learning Models for Nonstationary Tasks Inproceedings

Bartz-Beielstein, T; Filipic, B (Ed.): PPSN'2014: 13th International Conference on Parallel Problem Solving From Nature, Ljubljana, pp. 292–301, Springer, Heidelberg, 2014.

Links | BibTeX

Bagheri, Samineh; Thill, Markus; Koch, Patrick; Konen, Wolfgang

Online Adaptable Learning Rates for the Game Connect-4 Technical Report

CIplus (TR 03/2014), 2014, (Preprint version of the article in IEEE Transactions on Computational Intelligence and AI in Games, 2016).

Links | BibTeX

Thill, Markus; Bagheri, Samineh; Koch, Patrick; Konen, Wolfgang

Temporal Difference Learning with Eligibility Traces for the Game Connect-4 Inproceedings

Preuss, Mike ; Rudolph, Günther (Ed.): CIG'2014, International Conference on Computational Intelligence in Games, Dortmund, pp. 84 – 91, 2014.

Links | BibTeX

2012

Thill, Markus; Koch, Patrick; Konen, Wolfgang

Reinforcement learning with n-tuples on the game Connect-4 Inproceedings

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

Links | BibTeX

Thill, Markus

Reinforcement Learning mit N-Tupel-Systemen für Vier Gewinnt Masters Thesis

TH Köln -- University of Applied Sciences, 2012, (Bachelor thesis, 1st prize in Opitz award 2013, Festo award 2012, Ferchau award 2012).

Links | BibTeX

2011

Konen, Wolfgang

Self-configuration from a Machine-Learning Perspective Technical Report

Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (05/11; arXiv: 1105.1951), 2011, ISSN: 2191-365X, (e-print published at http://arxiv.org/abs/1105.1951 and Dagstuhl Preprint Archive, Workshop 11181 "Organic Computing -- Design of Self-Organizing Systems").

Links | BibTeX

2009

Konen, Wolfgang; Bartz-Beielstein, Thomas

Reinforcement learning for games: failures and successes -- CMA-ES and TDL in comparision Inproceedings

GECCO '09: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference, pp. 2641–2648, ACM, Montreal, Québec, Canada, 2009.

Links | BibTeX

Konen, Wolfgang; Bartz-Beielstein, Thomas

Evolutionsstrategien und Reinforcement Learning für strategische Brettspiele Technical Report

Cologne University of Applied Sciences 2009.

Links | BibTeX

2008

Konen, Wolfgang; Bartz-Beielstein, Thomas

Reinforcement Learning: Insights from Interesting Failures in Parameter Selection Inproceedings

Rudolph, Günter ; others, (Ed.): PPSN'2008: 10th International Conference on Parallel Problem Solving From Nature, Dortmund, pp. 478–487, Springer, Berlin, 2008.

Links | BibTeX

Konen, Wolfgang

Reinforcement Learning für Brettspiele: Der Temporal Difference Algorithmus Technical Report

Cologne University of Applied Sciences 2008.

Links | BibTeX

Konen, Wolfgang; Bartz-Beielstein, Thomas

Reinforcement Learning für strategische Brettspiele Technical Report

Cologne University of Applied Sciences 2008.

Links | BibTeX