Abstract
In this paper we present a new strategy game, with machine learning computer players, which have been developed using temporal difference reinforcement learning coupled with neural networks; the latter are used for value approximation and for storing the players’ knowledge. We set out the game rules and then design and implement a comprehensive experimentation session to allow us to explore a large state space for investigating learning and playing behavior, without placing unreasonable demands on speed and accuracy. Our experiments demonstrate how computer players manage to adapt to their environment and improve their tactic over time, based on experience only, while still accommodating a variety of behaviors which are tuned via the conventional parameters of the reinforcement learning and neural network mechanisms.
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
- 1.
The rest of the parameters are as follows: Variant = 6 × 5, ε-greedy = 0.9, gamma = 0.9, elimination reward = false, min-max reward = (−1, 1), opponent = CPU Defense.
References
Campbell, M., Hoane, A.J., Hsu, F.H.: Deep blue. Artif. Intell. 134(1–2), 57–83 (2002)
Tesauro, G.: Programming backgammon using self-teaching neural nets. Artif. Intell. 134(1–2), 181–199 (2002)
Papahristou, N., Refanidis, I.: Improving temporal difference learning performance in backgammon variants. In: Herik, H.J., Plaat, A. (eds.) ACG 2011. LNCS, vol. 7168, pp. 134–145. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31866-5_12
Knight, W.: Google’s AI masters the game of go a decade earlier than expected (2016), https://www.technologyreview.com/s/546066/googles-ai-masters-the-game-of-go-a-decade-earlier-than-expected/
Makris, V., Kalles, D.: Evolving multi-layer neural networks for Othello. In: 9th Hellenic Conference on Artificial Intelligence, Thessaloniki (2016)
Kalles, D., Kanellopoulos, P.: On verifying game design and playing strategies using reinforcement learning. In: Proceedings of ACM Symposium on Applied Computing, Special Track on Artificial Intelligence and Computation Logic, Las Vegas (2001)
Ram, A., Ontañón, S., Mehta, M.: Artificial intelligence for adaptive computer games. In: 20th International FLAIRS Conference on Artificial Intelligence (FLAIRS-2007). AAAI Press (2007)
Collection of Playable Experimental Games Created by Researchers in the Field of Artificial Intelligence (AI). http://www.aigameresearch.org/
Scott, J.P.: List of Online Game Learning Software (2001). http://satirist.org/learn-game/lists/software.html
Russell, S.J., Norving, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Pearson Higher Education, Upper Saddle River (2010)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, London (2012)
Ferber, J.: Multi-agent Systems: An Introduction to Distributed Artificial Intelligence. Addison-Wesley, Boston (1999)
Shoham, Y., Leyton, K.B.: Multiagent Systems: Algorithmic, Game-Theoretic and Logical Foundations. Cambridge University Press, New York (2009)
Marivate, V.N.: Social learning methods in board game agents. In: IEEE Symposium Computational Intelligence and Games, Perth, Australia, pp. 323–328 (2008)
Kiourt, C., Kalles, D.: Social reinforcement learning in game playing. In: IEEE International Conference on Tools with Artificial Intelligence, Athens, Greece, pp. 322–326 (2012)
Lopes, M., Melo, F.S., Kenward, B., Santos-Victor, J.: A computational model of social-learning mechanisms. Adapt. Behav. 17, 467–483 (2009)
Kiourt, C., Kalles, D.: Learning in multi agent social environments with opponent models. In: 13th European Conference on Multi-Agent Systems and 3rd International Conference on Agreement Technologies (EUMAS 2015 and AT 2015), pp. 137–144 (2016)
Kiourt, C., Kalles, D.: A platform for large-scale game-playing multi-agent systems on a high performance computing infrastructure. Int. J. Multiagent Grid Syst. 12(1), 35–54 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Nikolakakis, A., Kalles, D. (2017). Neural Networks as a Learning Component for Designing Board Games. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds) Engineering Applications of Neural Networks. EANN 2017. Communications in Computer and Information Science, vol 744. Springer, Cham. https://doi.org/10.1007/978-3-319-65172-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-65172-9_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65171-2
Online ISBN: 978-3-319-65172-9
eBook Packages: Computer ScienceComputer Science (R0)