Dizin Eklenmedi

Game Strategy Decision Module Based on GA and Neural Network

Received: Accepted: Published:
DOI:10.15340/2148188111929Pages:1-12

Abstract


 

This paper proposes an implementation solution for a strategy decision module. This module is intended to become the first layer of a bigger artificial intelligence. Traditionally each artificial intelligence is designed and programmed in order to be used for a specific purpose within a single software. However, our objective is to create an artificial intelligence adaptable to all kinds of games without any modification of its source code. This artificial intelligence is based on a three layers framework. The two first layers are respectively responsible to compute the global strategy and the sequence of elementary actions used to accomplish this one. The third layer is in charge to handle the emergency cases which are potentially endangering the artificial intelligence. In this paper, we focus on the first layer development and describe a solution based on an optimization algorithm coupled to a neural network. Through a series of experiments on various optimization algorithms, we determined that the genetic algorithm was the best suitable solution to our needs. The final experiments, proved the efficiency of our solution to adapt to various kinds of games.

 

Please purchase to download content


€4

Please purchase to download PDF


€4

References


 

Davis, L. (Ed.). (1991). Handbook of genetic algorithms (Vol. 115). New York: Van Nostrand Reinhold.
 
Dorigo, M., & Birattari, M. (2010). Ant colony optimization. In Encyclopedia of Machine Learning (pp. 36-39). Springer US.
 
Grefenstette, J. J. (Ed.). (2013). Genetic Algorithms and Their Applications: Proceedings of the Second International Conference on Genetic Algorithms. Psychology Press.
 
Harp, S. A., & Samad, T. (2013). Optimizing neural networks with genetic algorithms. In Proceedings of the 54th American Power Conference, Chicago (Vol. 2).
 
Hausknecht, M., Lehman, J., Miikkulainen, R., & Stone, P. (2013). A neuroevolution approach to general atari game playing.
 
Levine, J., Congdon, C. B., Ebner, M., Kendall, G., Lucas, S. M., Miikkulainen, R., ... & Thompson, T. (2013). General Video Game Playing. Artificial and Computational Intelligence in Games, 6, 77-83.
 
Naddaf, Y. (2010). Game-independent ai agents for playing atari 2600 console games. University of Alberta.
 
Nareyek, A. (2004). AI in computer games. Queue, 1(10), 58.
http://dx.doi.org/10.1145/971564.971593
 
Vallade, B., Alexandre, D., & Nakashima, T. (2014, December). Proposition of a three layers architecture for adaptable artificial intelligence. In Soft Computing and Intelligent Systems (SCIS), 2014 Joint 7th International Conference on and Advanced Intelligent Systems (ISIS), 15th International Symposium on (pp. 247-252). IEEE.
 
Vallade, B., & Nakashima, T. (2014). Improving Particle Swarm Optimization Algorithm and Its Application to Physical Travelling Salesman Problems with a Dynamic Search Space. In Applied Computing and Information Technology (pp. 105-119). Springer International Publishing.
http://dx.doi.org/10.1007/978-3-319-05717-0_8
 

Citation Information


Cited by articles

Cited by Google Scholar

Search GoogleScholar

Citation Management Tool



Altmetric Attention Score


Full Text Views

Cited by


Ethical Obligations Journal Sevices Contact us
Copyright © 2010-2017 MacroWorld Ltd. All Rights Reserved