Abstract
In our study the Battleship game we concern as an example of a simple pattern matching problem in correspondence with the Partially observable Markov decision process. We provide comparison of supervised and reinforcement learning paradigms used as neural network learning mechanisms applied by solving the Battleship game.We examine convergence of the neural network adaptation process by using these techniques.While concerning our pattern matching problem of the Battleship game solution by the neural network the reinforcement learning technique is not as straightforward as the supervised learning. On the other hand the neural network adaptation by the supervised learning mechanism has a faster convergence in our case. We use the Battleship game probability model to determine next position in an environment to be shot at with the highest probability of resulting into a successful hit attempt.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Abraham, A.: Hybrid soft computing and applications. International Journal of Computational Intelligence and Applications 8(1), 5–7 (2009)
Clementis, L.: Model driven classifier evaluation in rule-based system. In: Snasel, V., Abraham, A., Corchado, E.S. (eds.) SOCO Models in Industrial & Environmental Appl. AISC, vol. 188, pp. 267–276. Springer, Heidelberg (2013)
Corchado, A., Arroyo, A., Tricio, V.: Soft computing models to identify typical meteorological days. Logic Journal of the IGPL 19(2), 373–383 (2011)
Drugowitsch, J.: Design and Analysis of Learning Classifier Systems: A Probabilistic Approach. SCI. Springer, Heidelberg (2008)
Halavati, R., Shouraki, S., Lotfi, S., Esfandiar, P.: Symbiotic evolution of rule based classifier systems. International Journal on Artificial Intelligence Tools 18(1), 1–16 (2009)
Harmon, M., Harmon, S.: Reinforcement learning: A tutorial (1996), http://www.nbu.bg/cogs/events/2000/Readings/Petrov/rltutorial.pdf
Holland, J.: Adaptation in Natural and Artificial Systems. The University of Michigan Press, Ann Arbor (1975)
Holland, J.: Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. MIT Press, Cambridge (1992)
Kriesel, D.: A Brief Introduction to Neural Networks, Zeta version (2007), http://www.dkriesel.com
Krömer, P., Platos, J., Snášel, V., Abraham, A.: Fuzzy classification by evolutionary algorithms. In: SMC, pp. 313–318. IEEE (2011)
Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.): IWLCS 1999. LNCS (LNAI), vol. 1813. Springer, Heidelberg (2000)
Qudrat-Ullah, H., Spector, J., Davidsen, P.: Complex decision making: theory and practice. Understanding complex systems. Springer (2008), http://books.google.sk/books?id=DDs1ps3YRWQC
Sedano, J., Curiel, L., Corchado, E., de la Cal, E., Villar, J.: A soft computing method for detecting lifetime building thermal insulation failures. Integrated Computer-Aided Engineering 17(2), 103–115 (2010)
Smith, M.: Neural Networks for Statistical Modeling. Thomson Learning (1993)
Sutton, R., Barto, A.: Reinforcement learning: an introduction. Adaptive computation and machine learning. MIT Press (1998), http://books.google.sk/books?id=CAFR6IBF4xYC
Watkins, C., Dayan, P.: Q-learning. Machine Learning 8(3-4), 279–292 (1992), http://jmvidal.cse.sc.edu/library/watkins92a.pdf
Zadeh, L.: Fuzzy logic, neural networks, and soft computing. Communication of the ACM 37(3), 77–84 (1994)
Zelinka, I., Davendra, D.D., Chadli, M., Senkerik, R., Dao, T.T., Skanderova, L.: Evolutionary dynamics as the structure of complex networks. In: Zelinka, I., Snasel, V., Abraham, A. (eds.) Handbook of Optimization. ISRL, vol. 38, pp. 215–243. Springer, Heidelberg (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Clementis, L. (2013). Supervised and Reinforcement Learning in Neural Network Based Approach to the Battleship Game Strategy. In: Zelinka, I., Chen, G., Rössler, O., Snasel, V., Abraham, A. (eds) Nostradamus 2013: Prediction, Modeling and Analysis of Complex Systems. Advances in Intelligent Systems and Computing, vol 210. Springer, Heidelberg. https://doi.org/10.1007/978-3-319-00542-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-00542-3_20
Publisher Name: Springer, Heidelberg
Print ISBN: 978-3-319-00541-6
Online ISBN: 978-3-319-00542-3
eBook Packages: EngineeringEngineering (R0)