Connect-4 Game Playing Framework (C4GPF).png "Connect-4 board. Red to move. Red is under zugzwang and will loose the game. The numbers indicate the states of some so-called \"n-tuples\".")
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
2023
Konen, Wolfgang
Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning Journal Article
In: arXiv preprint arXiv:2301.12167, 2023.
@article{Konen2023b,
title = {Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning},
author = {Wolfgang Konen},
url = {https://arxiv.org/abs/2301.12167},
year = {2023},
date = {2023-01-01},
journal = {arXiv preprint arXiv:2301.12167},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
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 Masters Thesis
TH Köln – University of Applied Sciences, 2023, (Bachelor thesis).
@mastersthesis{Seven2023,
title = {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},
author = {Meltem Seven},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA_Meltem-Seven-final.pdf},
year = {2023},
date = {2023-01-01},
school = {TH Köln – University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
2022
Konen, Wolfgang
The GBG Class Interface Tutorial V2.3: General Board Game Playing and Learning Technical Report
TH Köln 2022.
@techreport{Konen2022a,
title = {The GBG Class Interface Tutorial V2.3: General Board Game Playing and Learning},
author = {Wolfgang Konen},
url = {https://www.gm.fh-koeln.de/ciopwebpub/Konen22a.d/TR-GBG.pdf},
year = {2022},
date = {2022-09-01},
institution = {TH Köln},
school = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Fabig, Niklas
Reinforcement Learning für Standard Operating Procedures einer Atomkraftwerkssimulation Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Master thesis).
@mastersthesis{Fabig2022,
title = {Reinforcement Learning für Standard Operating Procedures einer Atomkraftwerkssimulation},
author = {Niklas Fabig},
year = {2022},
date = {2022-08-01},
urldate = {2022-08-01},
school = {TH Köln -- University of Applied Sciences},
note = {Master thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Weitz, Ann
Untersuchung von selbstlernenden Reinforcement Learning Agenten im computergenerierten Spiel Yavalath Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Bachelor thesis).
@mastersthesis{Weitz2022b,
title = {Untersuchung von selbstlernenden Reinforcement Learning Agenten im computergenerierten Spiel Yavalath},
author = {Ann Weitz},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-Weitz-final-2022.pdf},
year = {2022},
date = {2022-05-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Raycheva, Ralitsa
Reinforcement Learning in Simulationsspielen: Repräsentation von großen Aktions- und Zustandsräumen am Beispiel von Ökolopoly Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Bachelor thesis).
@mastersthesis{Raycheva2022,
title = {Reinforcement Learning in Simulationsspielen: Repräsentation von großen Aktions- und Zustandsräumen am Beispiel von Ökolopoly},
author = {Ralitsa Raycheva},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-Raycheva2022-final.pdf},
year = {2022},
date = {2022-02-01},
urldate = {2022-02-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Cöln, Julian
KI-Konzepte für das Erlernen nicht-deterministischer Spiele am Beispiel von "EinStein würfelt nicht!" Masters Thesis
TH Köln -- University of Applied Sciences, 2022, (Bachelor thesis).
@mastersthesis{Cöln2022,
title = {KI-Konzepte für das Erlernen nicht-deterministischer Spiele am Beispiel von "EinStein würfelt nicht!"},
author = {Julian Cöln},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA_Julian_Coeln2021-final.pdf},
year = {2022},
date = {2022-02-01},
urldate = {2022-02-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Weitz, Ann
Entwicklung einer allgemeinen Schnittstelle zwischen Ludii und dem GBG Framework Technical Report
TH Köln -- University of Applied Sciences 2022, (Praxisprojekt).
@techreport{Weitz2022,
title = {Entwicklung einer allgemeinen Schnittstelle zwischen Ludii und dem GBG Framework},
author = {Ann Weitz},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/PP-Doku-Weitz-2022-02.pdf},
year = {2022},
date = {2022-02-01},
institution = {TH Köln -- University of Applied Sciences},
note = {Praxisprojekt},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Scheiermann, Johannes; Konen, Wolfgang
AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time Journal Article
In: IEEE Transactions on Games, 2022.
@article{Scheier2022,
title = {AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time},
author = {Johannes Scheiermann and Wolfgang Konen},
url = {https://ieeexplore.ieee.org/document/9893320},
doi = {10.1109/TG.2022.3206733},
year = {2022},
date = {2022-01-01},
journal = {IEEE Transactions on Games},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Scheiermann, Johannes; Konen, Wolfgang
AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time Journal Article
In: arXiv preprint arXiv:2204.13307, 2022, (Preprint of the IEEE ToG 2022 paper).
@article{Scheier2022arXiv,
title = {AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time},
author = {Johannes Scheiermann and Wolfgang Konen},
url = {https://arxiv.org/abs/2204.13307},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {arXiv preprint arXiv:2204.13307},
note = {Preprint of the IEEE ToG 2022 paper},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
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) Masters Thesis
TH Köln -- University of Applied Sciences, 2021, (Bachelor thesis).
@mastersthesis{Meissner2021,
title = {Untersuchung des Spiel- und Lernerfolgs künstlicher Intelligenzen für ein nichtdeterministisches Spiel mit imperfekten Informationen: Blackjack in der Game-Learning-Umgebung ’General Board Game’ (GBG)},
author = {Simon Meissner},
url = {https://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-Meissner-final-2021.pdf},
year = {2021},
date = {2021-12-01},
urldate = {2021-12-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Zeh, Tim
Untersuchung von allgemeinen KI-Agenten für das Spiel Poker im General Board Games Framework Masters Thesis
TH Köln -- University of Applied Sciences, 2021, (Master thesis).
@mastersthesis{Zeh2021,
title = {Untersuchung von allgemeinen KI-Agenten für das Spiel Poker im General Board Games Framework},
author = {Tim Zeh},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/MA_Zeh_final_Poker-GBG-2021.pdf},
year = {2021},
date = {2021-01-01},
school = {TH Köln -- University of Applied Sciences},
note = {Master thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Raycheva, Ralitsa
Erstellung eines Custom Environments in OpenAI Gym für das Spiel Ökolopoly Technical Report
TH Köln -- University of Applied Sciences 2021, (Praxisprojekt).
@techreport{Raycheva2021,
title = {Erstellung eines Custom Environments in OpenAI Gym für das Spiel Ökolopoly},
author = {Ralitsa Raycheva},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/PP_Oekolopoly_Raycheva_final.pdf},
year = {2021},
date = {2021-01-01},
institution = {TH Köln -- University of Applied Sciences},
note = {Praxisprojekt},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Konen, Wolfgang; Bagheri, Samineh
Final adaptation reinforcement learning for N-player games Journal Article
In: arXiv preprint arXiv:2111.14375, 2021.
@article{konen2021final,
title = {Final adaptation reinforcement learning for N-player games},
author = {Wolfgang Konen and Samineh Bagheri},
url = {https://arxiv.org/abs/2111.14375},
year = {2021},
date = {2021-01-01},
journal = {arXiv preprint arXiv:2111.14375},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
Scheiermann, Johannes
AlphaZero-inspirierte KI-Agenten im General Board Game Playing Masters Thesis
TH Köln -- University of Applied Sciences, 2020, (Bachelor thesis).
@mastersthesis{Scheier2020b,
title = {AlphaZero-inspirierte KI-Agenten im General Board Game Playing},
author = {Johannes Scheiermann},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA_Scheiermann_final.pdf},
year = {2020},
date = {2020-12-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Konen, Wolfgang; Bagheri, Samineh
Reinforcement Learning for N-Player Games: The Importance of Final Adaptation Proceedings Article
In: Vasile, Massimiliano; Filipic, Bogdan (Ed.): 9th International Conference on Bioinspired Optimisation Methods and Their Applications (BIOMA)
, Bruxelles. Video (15 min) + slides available at https://youtu.be/OcpX7ITeH9w, 2020.
@inproceedings{Konen20b,
title = {Reinforcement Learning for N-Player Games: The Importance of Final Adaptation},
author = {Wolfgang Konen and Samineh Bagheri},
editor = {Massimiliano Vasile and Bogdan Filipic },
url = {https://www.gm.fh-koeln.de/ciopwebpub/Konen20b.d/bioma20-TDNTuple.pdf},
year = {2020},
date = {2020-10-01},
urldate = {2020-10-01},
booktitle = {9th International Conference on Bioinspired Optimisation Methods and Their Applications (BIOMA)
},
address = {Bruxelles. Video (15 min) + slides available at https://youtu.be/OcpX7ITeH9w},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Konen, Wolfgang
The GBG Class Interface Tutorial V2.2: General Board Game Playing and Learning Technical Report
Research Center CIOP (Computational Intelligence, Optimization and Data Mining), Oct 2020.
@techreport{Konen20d,
title = {The GBG Class Interface Tutorial V2.2: General Board Game Playing and Learning},
author = {Wolfgang Konen},
url = {https://www.gm.fh-koeln.de/ciopwebpub/Konen20d.d/TR-GBG.pdf},
year = {2020},
date = {2020-01-10},
urldate = {2020-01-10},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining), Oct},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Konen, Wolfgang; Bagheri, Samineh
Final Adaptation Reinforcement Learning for N-Player Games Technical Report
Research Center CIOP (Computational Intelligence, Optimization and Data Mining) 2020.
@techreport{Konen20b_TR,
title = {Final Adaptation Reinforcement Learning for N-Player Games},
author = {Wolfgang Konen and Samineh Bagheri},
url = {https://www.gm.fh-koeln.de/ciopwebpub/Konen20b_TR.d/Konen20b_TR.pdf},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Scheiermann, Johannes
Sind (trainierte) General-Purpose-RL-Agenten im Brettspiel Othello stärker als (untrainierte) General-Game-Playing Agenten? Technical Report
TH Köln, Institut für Informatik 2020, (Praxisprojekt).
@techreport{Scheier2020,
title = {Sind (trainierte) General-Purpose-RL-Agenten im Brettspiel Othello stärker als (untrainierte) General-Game-Playing Agenten?},
author = {Johannes Scheiermann},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/INF-Prj-Scheiermann-2020-08.pdf},
year = {2020},
date = {2020-01-01},
institution = {TH Köln, Institut für Informatik},
note = {Praxisprojekt},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2019
Konen, Wolfgang
General Board Game Playing for Education and Research in Generic AI Game Learning Proceedings Article
In: Perez, Diego; Mostaghim, Sanaz; Lucas, Simon (Ed.): IEEE Conference on Games, London, 2019.
@inproceedings{Konen19b,
title = {General Board Game Playing for Education and Research in Generic AI Game Learning},
author = {Wolfgang Konen},
editor = {Diego Perez and Sanaz Mostaghim and Simon Lucas},
url = {https://arxiv.org/pdf/1907.06508},
year = {2019},
date = {2019-08-20},
booktitle = {IEEE Conference on Games},
address = {London},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Konen, Wolfgang
The GBG Class Interface Tutorial V2.0: General Board Game Playing and Learning Technical Report
Research Center CIOP (Computational Intelligence, Optimization and Data Mining) 2019.
@techreport{Konen19a,
title = {The GBG Class Interface Tutorial V2.0: General Board Game Playing and Learning},
author = {Wolfgang Konen},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Kone19a.d/TR-GBG.pdf},
year = {2019},
date = {2019-01-01},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Barsnick, Felix
Implementierung und Untersuchung eines Turniersystems für KI-Agenten in Brettspielen Masters Thesis
TH Köln -- University of Applied Sciences, 2019, (Master thesis).
@mastersthesis{Barsnick2019,
title = {Implementierung und Untersuchung eines Turniersystems für KI-Agenten in Brettspielen},
author = {Felix Barsnick},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/MA_MMI_Barsnick-2019-04-final.pdf},
year = {2019},
date = {2019-01-01},
institution = {Institut für Informatik},
school = {TH Köln -- University of Applied Sciences},
note = {Master thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Cöln, Julian; Dittmar, Yannick
Untersuchung von KI Agenten im Spiel Othello Technical Report
TH Köln, Institut für Informatik 2019.
@techreport{Cöln2019,
title = {Untersuchung von KI Agenten im Spiel Othello},
author = {Julian Cöln and Yannick Dittmar},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/INF-Proj-DittmarCoeln-2019-12.pdf},
year = {2019},
date = {2019-01-01},
institution = {TH Köln, Institut für Informatik},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2017
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).
@mastersthesis{Galitzki2017,
title = {Selbstlernende Agenten für das skalierbare Spiel Hex: Untersuchung verschiedener KI-Verfahren im GBG-Framework},
author = {Kevin Galitzki},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA-KevinGalitzki-final-2017.pdf},
year = {2017},
date = {2017-09-15},
institution = {Institut für Informatik},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
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).
@techreport{Kone17a,
title = {The GBG Class Interface Tutorial: General Board Game Playing and Learning},
author = {Konen, Wolfgang},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Kone17a.d/TR-GBG.pdf},
year = {2017},
date = {2017-06-01},
address = {Cologne University of Applied Science},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
note = {e-print published at http://www.gm.fh-koeln.de/ciopwebpub/Kone17a.d/TR-GBG.pdf},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
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, 2nd prize in CBC award 2018).
@mastersthesis{Kutsch2017b,
title = {KI-Agenten fur das Spiel 2048: Untersuchung von Lernalgorithmen für nichtdeterministische Spiele},
author = {Johannes Kutsch},
url = {http://www.gm.fh-koeln.de/~konen/research/PaperPDF/BA_JohannesKutsch_Final-2017.pdf},
year = {2017},
date = {2017-01-01},
institution = {Institut für Informatik},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis, 2nd prize in CBC award 2018},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
2016
Bagheri, Samineh; Thill, Markus; Koch, Patrick; Konen, Wolfgang
Online Adaptable Learning Rates for the Game Connect-4 Journal Article
In: IEEE Transactions on Computational Intelligence and AI in Games, vol. 8, no. 1, pp. 33-42, 2016, (accepted 11/2014).
@article{Bagh16b,
title = {Online Adaptable Learning Rates for the Game Connect-4},
author = { Samineh Bagheri and Markus Thill and Patrick Koch and Wolfgang Konen},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen//Bagh15.pdf},
doi = {10.1109/TCIAIG.2014.2367105},
year = {2016},
date = {2016-01-01},
journal = {IEEE Transactions on Computational Intelligence and AI in Games},
volume = {8},
number = {1},
pages = {33-42},
note = {accepted 11/2014},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
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.
@techreport{Kone15c,
title = {Reinforcement Learning for Board Games: The Temporal Difference Algorithm},
author = { Wolfgang Konen},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Kone15c.d/TR-TDgame_EN.pdf},
doi = {10.13140/RG.2.1.1965.2329},
year = {2015},
date = {2015-07-01},
address = {Cologne University of Applied Sciences},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
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).
@techreport{Kone15a,
title = {Reinforcement Learning für Brettspiele: Der Temporal Difference Algorithmus},
author = { Wolfgang Konen},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Kone15a.d/TR-TDgame.pdf},
year = {2015},
date = {2015-00-01},
address = {Cologne University of Applied Science},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
note = {Updated version 2015},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2014
Thill, Markus; Konen, Wolfgang
Connect-4 Game Playing Framework (C4GPF) Miscellaneous
2014.
@misc{ThilKon14,
title = {Connect-4 Game Playing Framework (C4GPF)},
author = { Markus Thill and Wolfgang Konen},
url = {http://github.com/MarkusThill/Connect-Four},
year = {2014},
date = {2014-10-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
Konen, Wolfgang; Koch, Patrick
Adaptation in Nonlinear Learning Models for Nonstationary Tasks Proceedings Article
In: Bartz-Beielstein, T.; Filipic, B. (Ed.): PPSN'2014: 13th International Conference on Parallel Problem Solving From Nature, Ljubljana, pp. 292–301, Springer, Heidelberg, 2014.
@inproceedings{Kone14a,
title = {Adaptation in Nonlinear Learning Models for Nonstationary Tasks},
author = { Wolfgang Konen and Patrick Koch},
editor = {Bartz-Beielstein, T. and Filipic, B.},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/Kone14a-Adaptation.pdf},
year = {2014},
date = {2014-09-01},
booktitle = {PPSN'2014: 13th International Conference on Parallel Problem Solving From Nature, Ljubljana},
pages = {292--301},
publisher = {Springer},
address = {Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bagheri, Samineh; Thill, Markus; Koch, Patrick; Konen, Wolfgang
Online Adaptable Learning Rates for the Game Connect-4 Technical Report
CIplus no. TR 03/2014, 2014, (Preprint version of the article in IEEE Transactions on Computational Intelligence and AI in Games, 2016).
@techreport{Bagh14a,
title = {Online Adaptable Learning Rates for the Game Connect-4},
author = { Samineh Bagheri and Markus Thill and Patrick Koch and Wolfgang Konen},
url = {http://nbn-resolving.de/urn:nbn:de:hbz:832-cos-704},
doi = {10.1109/TCIAIG.2014.2367105},
year = {2014},
date = {2014-01-01},
number = {TR 03/2014},
institution = {CIplus},
note = {Preprint version of the article in IEEE Transactions on Computational Intelligence and AI in Games, 2016},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Thill, Markus; Bagheri, Samineh; Koch, Patrick; Konen, Wolfgang
Temporal Difference Learning with Eligibility Traces for the Game Connect-4 Proceedings Article
In: Preuss, Mike; Rudolph, Günther (Ed.): CIG'2014, International Conference on Computational Intelligence in Games, Dortmund, pp. 84 – 91, 2014.
@inproceedings{Thil14,
title = {Temporal Difference Learning with Eligibility Traces for the Game Connect-4},
author = { Markus Thill and Samineh Bagheri and Patrick Koch and Wolfgang Konen},
editor = {Preuss, Mike and Rudolph, Günther},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/ThillCIG2014.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {CIG'2014, International Conference on Computational Intelligence in Games, Dortmund},
pages = {84 -- 91},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2012
Thill, Markus; Koch, Patrick; Konen, Wolfgang
Reinforcement learning with n-tuples on the game Connect-4 Proceedings Article
In: 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.
@inproceedings{Thil12,
title = {Reinforcement learning with n-tuples on the game Connect-4},
author = { Markus Thill and Patrick Koch and Wolfgang Konen},
editor = {Coello Coello, Carlos and Cutello, Vincenzo and others},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Thi12.d/Thil12.pdf},
year = {2012},
date = {2012-09-01},
booktitle = {PPSN'2012: 12th International Conference on Parallel Problem Solving From Nature, Taormina},
pages = {184--194},
publisher = {Springer},
address = {Heidelberg},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
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).
@mastersthesis{Thill12,
title = {Reinforcement Learning mit N-Tupel-Systemen für Vier Gewinnt},
author = {Thill, Markus},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Theses.d/Thill12.d/BA-Thill-2012.pdf},
year = {2012},
date = {2012-07-01},
school = {TH Köln -- University of Applied Sciences},
note = {Bachelor thesis, 1st prize in Opitz award 2013, Festo award 2012, Ferchau award 2012},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
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, no. 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").
@techreport{Kone11c,
title = {Self-configuration from a Machine-Learning Perspective},
author = { Wolfgang Konen},
url = {http://www.gm.fh-koeln.de/ciopwebpub/Kone11c.d/Kone11c.pdf},
issn = {2191-365X},
year = {2011},
date = {2011-05-01},
number = {05/11; arXiv: 1105.1951},
address = {Cologne University of Applied Science, Faculty of Computer Science and Engineering Science},
institution = {Research Center CIOP (Computational Intelligence, Optimization and Data Mining)},
note = {e-print published at http://arxiv.org/abs/1105.1951 and Dagstuhl Preprint Archive, Workshop 11181 "Organic Computing -- Design of Self-Organizing Systems"},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2009
Konen, Wolfgang; Bartz-Beielstein, Thomas
Reinforcement learning for games: failures and successes -- CMA-ES and TDL in comparision Proceedings Article
In: GECCO '09: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference, pp. 2641–2648, ACM, Montreal, Québec, Canada, 2009.
@inproceedings{Kone09a,
title = {Reinforcement learning for games: failures and successes -- CMA-ES and TDL in comparision},
author = { Wolfgang Konen and Thomas Bartz-Beielstein},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/evo-reinforce-GECCO2009.pdf},
doi = {http://doi.acm.org/10.1145/1570256.1570375},
year = {2009},
date = {2009-01-01},
booktitle = {GECCO '09: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference},
pages = {2641--2648},
publisher = {ACM},
address = {Montreal, Québec, Canada},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Konen, Wolfgang; Bartz-Beielstein, Thomas
Evolutionsstrategien und Reinforcement Learning für strategische Brettspiele Technical Report
Cologne University of Applied Sciences 2009.
@techreport{KoneB09,
title = {Evolutionsstrategien und Reinforcement Learning für strategische Brettspiele},
author = { Wolfgang Konen and Thomas Bartz-Beielstein},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/FBericht2009-RL-Kg-Bi.pdf},
year = {2009},
date = {2009-01-01},
institution = {Cologne University of Applied Sciences},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2008
Konen, Wolfgang; Bartz-Beielstein, Thomas
Reinforcement Learning: Insights from Interesting Failures in Parameter Selection Proceedings Article
In: Rudolph, Günter; others, (Ed.): PPSN'2008: 10th International Conference on Parallel Problem Solving From Nature, Dortmund, pp. 478–487, Springer, Berlin, 2008.
@inproceedings{Kone08a,
title = {Reinforcement Learning: Insights from Interesting Failures in Parameter Selection},
author = { Wolfgang Konen and Thomas Bartz-Beielstein},
editor = {Rudolph, Günter and others},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/ppsn2008.pdf},
year = {2008},
date = {2008-09-01},
booktitle = {PPSN'2008: 10th International Conference on Parallel Problem Solving From Nature, Dortmund},
pages = {478--487},
publisher = {Springer},
address = {Berlin},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Konen, Wolfgang
Reinforcement Learning für Brettspiele: Der Temporal Difference Algorithmus Technical Report
Cologne University of Applied Sciences 2008.
@techreport{Kone08b,
title = {Reinforcement Learning für Brettspiele: Der Temporal Difference Algorithmus},
author = { Wolfgang Konen},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/TR_TDlambda2008.pdf},
year = {2008},
date = {2008-01-01},
institution = {Cologne University of Applied Sciences},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
Konen, Wolfgang; Bartz-Beielstein, Thomas
Reinforcement Learning für strategische Brettspiele Technical Report
Cologne University of Applied Sciences 2008.
@techreport{Kone08c,
title = {Reinforcement Learning für strategische Brettspiele},
author = { Wolfgang Konen and Thomas Bartz-Beielstein},
url = {http://www.gm.fh-koeln.de/~konen/Publikationen/FBericht2008-Kg-Bi-RL-Brettspiele.pdf},
year = {2008},
date = {2008-01-01},
institution = {Cologne University of Applied Sciences},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
