Game Learning
(see also: GBG: General Board Games in CIOP and Neue Themenangebote im Bereich Game Learning)
Games are of interest to me concerning their strategies and concerning the question whether a computer can learn these strategies just from self-play, without explicitly programming the tactics or performing exhaustive search.
In our research group we study extensively the game "Connect-4" ("Four-in-a-Row"). We were able to develop an agent which learns Connect-4 nearly perfectly just from self-play. Our Java-based Connect-4 Game Playing Framework (C4GPF) is now open-source for interested researchers. Read more…
The long-term goal of our research group is it to transfer these learning strategies to other games as well (2048, dots-and-boxes, go, chess, checkers, Abalone, Sim, …). The related research field is known as General Game Playing (GGP). The aim of GGP is it to develop agents which are able to learn a great variety of games.
The teaching course WPF Spiele + Simulation (in German) gives an introduction to the foundations of simulation, their application in games and in game physics, which deals with realistic kinematics and dynamics for video game worlds.
Project members
![]() |
Samineh Bagheri, M.Sc., TH Köln |
![]() |
Markus Thill, M.Sc., TH Köln |
![]() |
Dr. Patrick Koch, TH Köln |
![]() |
Prof. Dr. Wolfgang Konen, TH Köln |
Publications Games
1. | General Board Game Playing for Education and Research in Generic AI Game Learning. In: Perez, Diego; Mostaghim, Sanaz; Lucas, Simon (Ed.): IEEE Conference on Games, London, 2019. | :
2. | SACOBRA with Online Whitening for Solving Optimization Problems with High Conditioning. arXiv preprint arXiv:1904.08397 2019. | :
3. | Solving Optimization Problems with High Conditioning by Means of Online Whitening. In: Lopez-Ibanez, Manuel (Ed.): Genetic and Evolutionary Computation Conference 2019 (GECCO'19), Prague, pp. 243-244, ACM, 2019. | :
4. | How to Solve the Dilemma of Margin-Based Equality Constraint Handling Methods. In: at-Automatisierungstechnik, submitted , 2019. | :
5. | Deep Learning mit Keras und Tensorflow. Vortrag auf DEBRL2019 (Digital Exchange Bergisches Rheinland 2019), 2019. | :
6. | The GBG Class Interface Tutorial V2.0: General Board Game Playing and Learning. Research Center CIOP (Computational Intelligence, Optimization and Data Mining) 2019. | :
7. | Implementierung und Untersuchung eines Turniersystems für KI-Agenten in Brettspielen. TH Köln -- University of Applied Sciences, 2019, (Master thesis). | :
8. | How to Solve the Dilemma of Margin-Based Equality Handling Methods. In: Hoffmann, Frank; Hüllermeier, Eyke; Mikut, Ralf (Ed.): Proceedings - 28. Workshop Computational Intelligence, Dortmund, 29. - 30. November 2018, pp. 257-270, KIT Scientific Publishing, Karlsruhe, 2018, ISBN: 978-3-7315-0845-8, (**Young Author Award**). | :
9. | Online Adaptable Time Series Anomaly Detection with Discrete Wavelet Transforms and Multivariate Gaussian Distributions. Research Center CIOP (Computational Intelligence, Optimization and Data Mining) TH Köln - University of Applied Science, 2018, (submitted to Archives of Data Sciences, Series A (ECDA'2018), preprint available at http://www.gm.fh-koeln.de/ciopwebpub/Thill18a.d/AoDS2018.pdf). | :
10. | The TDMR 2.0 Package: Tuned Data Mining in R. Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (02/2018), 2018, (Last update: April 2018 (original version: 2012)). | :
11. | The TDMR 2.0 Tutorial: Examples for Tuned Data Mining in R. Research Center CIOP (Computational Intelligence, Optimization and Data Mining) Cologne University of Applied Science, Faculty of Computer Science and Engineering Science, (03/2018), 2018, (Last update: April 2018 (original version: 2012)). | :
12. | Comparing Kriging and Radial Basis Function Surrogates. In: Hoffmann, Frank; Hüllermeier, Eyke (Ed.): Proceedings 27. Workshop Computational Intelligence, pp. 243-259, Universitätsverlag Karlsruhe, 2017. | :
13. | Anomaly Detection in Time Series with Discrete Wavelet Transforms and Maximum Likelihood Estimation. In: Hoffmann, Frank; Hüllermeier, Eyke (Ed.): Proceedings 27. Workshop Computational Intelligence, pp. 67-71, Universitätsverlag Karlsruhe, 2017. | :
14. | KI-Agenten fur das Spiel 2048: Untersuchung von Lernalgorithmen für nichtdeterministische Spiele. TH Köln -- University of Applied Sciences, 2017, (Bachelor thesis). | :
15. | Selbstlernende Agenten für das skalierbare Spiel Hex: Untersuchung verschiedener KI-Verfahren im GBG-Framework. TH Köln -- University of Applied Sciences, 2017, (Bachelor thesis). | :
16. | Time Series Anomaly Detection with Discrete Wavelet Transforms and Maximum Likelihood Estimation. In: Valenzuela, Olga; Rojas, Ignacio; others, (Ed.): International Work-Conference on Time Series (ITISE2017), 2017. | :
17. | Constraint Handling in Efficient Global Optimization. In: Bosman, Peter A N (Ed.): Genetic and Evolutionary Computation Conference 2017 (GECCO'17), Berlin, pp. 1, ACM, 2017. | :
18. | The GBG Class Interface Tutorial: General Board Game Playing and Learning. 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). | :
19. | Identifizierung von Anomalien in Zeitreihen mit Deep Autoencodern. TH Köln -- University of Applied Sciences, 2017, (Bachelor thesis). | :
20. | Self-adjusting parameter control for surrogate-assisted constrained optimization under limited budgets. In: Applied Soft Computing, 61 , pp. 377-393, 2017, ISSN: 1568-4946. | :
2019 |
General Board Game Playing for Education and Research in Generic AI Game Learning Inproceedings Perez, Diego; Mostaghim, Sanaz; Lucas, Simon (Ed.): IEEE Conference on Games, London, 2019. |
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. |
Implementierung und Untersuchung eines Turniersystems für KI-Agenten in Brettspielen Masters Thesis TH Köln -- University of Applied Sciences, 2019, (Master thesis). |
2017 |
KI-Agenten fur das Spiel 2048: Untersuchung von Lernalgorithmen für nichtdeterministische Spiele Masters Thesis TH Köln -- University of Applied Sciences, 2017, (Bachelor thesis). |
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). |
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). |
2016 |
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). |
2015 |
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. |
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). |
2014 |
Connect-4 Game Playing Framework (C4GPF) Miscellaneous 2014. |
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. |
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). |
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. |
2012 |
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. |
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). |
2011 |
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"). |
2009 |
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. |
Evolutionsstrategien und Reinforcement Learning für strategische Brettspiele Technical Report Cologne University of Applied Sciences 2009. |
2008 |
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. |
Reinforcement Learning für Brettspiele: Der Temporal Difference Algorithmus Technical Report Cologne University of Applied Sciences 2008. |
Reinforcement Learning für strategische Brettspiele Technical Report Cologne University of Applied Sciences 2008. |