Abstract
The field of general intelligence is one, where humans can still easily outperform machines. In the context of our work we describe it as the ability to learn an activity, like playing a game, without any prior knowledge of goals and rules. The agent has to learn by doing/playing and examining the consequences of its actions. Many traditional techniques in reinforcement learning, such as SARSA and Q-Learning, can provide a good solution to this category of problems. In our paper, however, we propose an alternative method based on evolutionary algorithms to overcome the extensive computing for all state-action pairs needed in traditional approaches. We have evaluated various parent selection algorithms and two different fitness functions. “The General Video Game AI Competition” (GVGAI), where contestants submit a playing agent programmed with some learning algorithm to be tested against unknown games, has been used as a benchmark for the performance of our implementation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Back, T.: Selective pressure in evolutionary algorithms: a characterization of selection mechanisms. In: Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence, vol. 1, pp. 57–62, June 1994. https://doi.org/10.1109/ICEC.1994.350042
Baker, J.E.: Reducing bias and inefficiency in the selection algorithm. In: Proceedings of the Second International Conference on Genetic Algorithms on Genetic Algorithms and Their Application, pp. 14–21. L. Erlbaum Associates Inc., Hillsdale (1987). http://dl.acm.org/citation.cfm?id=42512.42515
Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. Natural Computing Series, 2nd edn. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-44874-8. http://d-nb.info/1055840826/04
Gerdes, I., Klawonn, F., Kruse, R.: Evolutionäre Algorithmen: genetische Algorithmen - Strategien und Optimierungsverfahren - Beispielanwendungen. Computational intelligence, Wiesbaden, 1. aufl. edn. (2004). http://scans.hebis.de/HEBCGI/show.pl?12308575_toc.pdf
Holland, J.H.: Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. MIT Press, Cambridge (1992)
Michalewicz, Z.: Genetic algorithms + data structures: = evolution programs: with 36 tables. Berlin [u.a.], 3, rev. and extended ed. edn. (1996). http://scans.hebis.de/HEBCGI/show.pl?04961015_toc.pdf
Ronald, S.: Duplicate genotypes in a genetic algorithm. In: 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence, Cat. No. 98TH8360, pp. 793–798, May 1998. https://doi.org/10.1109/ICEC.1998.700153
Schaul, T.: A video game description language for model-based or interactive learning. In: 2013 IEEE Conference on Computational Intelligence in Games, CIG, pp. 1–8, August 2013. https://doi.org/10.1109/CIG.2013.6633610
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Balabanov, K., Logofătu, D. (2019). Developing a General Video Game AI Controller Based on an Evolutionary Approach. In: Nguyen, N., Gaol, F., Hong, TP., Trawiński, B. (eds) Intelligent Information and Database Systems. ACIIDS 2019. Lecture Notes in Computer Science(), vol 11431. Springer, Cham. https://doi.org/10.1007/978-3-030-14799-0_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-14799-0_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-14798-3
Online ISBN: 978-3-030-14799-0
eBook Packages: Computer ScienceComputer Science (R0)