Abstract
This paper proposes an artificial player for the Turtle Race game, with the goal of creating an opponent that will provide some amount of challenge to a human player. Turtle Race is a game of imperfect information, where the players know which one of the game pieces is theirs, but do not know which ones belong to the other players and which ones are neutral. Moreover, movement of the pieces is determined by cards randomly drawn from a deck. The artificial player is based on a non-linear neural network whose training is performed by means of a novel parallel evolutionary algorithm with fitness diversity adaptation. The algorithm handles, in parallel, several populations which cooperate with each other by exchanging individuals when a population registers a diversity loss. Four popular evolutionary algorithms have been tested for the proposed parallel framework. Numerical results show that an evolution strategy can be very efficient for the problem under examination and that the proposed adaptation tends to improve upon the algorithmic performance without any addition in computational overhead. The resulting artificial player displayed a high performance against other artificial players and a challenging behavior for expert human players.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lucas, S., Kendall, G.: Evolutionary computation and games. IEEE Computational Intelligence Magazine 1, 10–18 (2006)
Fogel, D.: Using evolutionary programming to create networks that are capable of playing tic-tac-toe. In: Proceedings of IEEE International Conference on Neural Networks, pp. 875–880 (1993)
Richards, N., Moriarty, D., Miikkulainen, R.: Evolving neural networks to play go. Applied Intelligence 8, 85–96 (1998)
Runarsson, T.P., Lucas, S.M.: Coevolution versus self-play temporal difference learning for acquiring position evaluation in small-board go. IEEE Transactions on Evolutionary Computation 9, 628–640 (2005)
Chellapilla, K., Fogel, D.: Evolving an expert checkers playing program without using human expertise. IEEE Transactions on Evolutionary Computation 5, 422–428 (2001)
Moraglio, A., Togelius, J.: Geometric particle swarm optimization for the sudoku puzzle. In: GECCO 2007: Proceedings of the 9th annual conference on Genetic and evolutionary computation, pp. 118–125 (2007)
Fudenberg, D., Tirole, J.: Game Theory. MIT Press, Cambridge (1993)
Barricelli, N.A.: Esempi numerici di processi di evoluzione. Methodos, 45–68 (1954)
Barone, L., While, L.: Evolving adaptive play for simplified poker. In: Proceedings of IEEE Intl. Conf. on Computational Intelligence (ICEC 1998), pp. 108–113 (1998)
Jaśkowski, W., Krawiec, K., Wieloch, B.: Evolving strategy for a probabilistic game of imperfect information using genetic programming. Journal Genetic Programming and Evolvable Machines 9, 281–294 (2008)
Engelbrecht, A.P.: Computational Intelligence: An Introduction. John Wiley & Sons Ltd., Chichester (2002)
Bourg, D.M., Seemann, G.: AI for Game Developers. O’Reilly, Sebastopol (2004)
Chellapilla, K., Fogel, D.: Evolution, neural networks, games, and intelligence. Proceedings of the IEEE 87, 1471–1496 (1999)
Abramson, B.: Expected-outcome: a general model of static evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 182–193 (1990)
Bürgmann, B.: Monte carlo go. IEEE Transactions on Pattern Analysis and Machine Intelligence 12, 182–193 (1993)
Storn, R., Price, K.: Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. Journal on Global Optimization 11, 341–359 (1997)
Price, K.V., Storn, R.M., Lampinen, J.A.: Differential Evolution–A Practical Approach to Global Optimization. Springer, Heidelberg (2005)
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: IEEE International Conference on Neural Networks, vol. 4, pp. 1942–1948 (1995)
Rechemberg, I.: Evolutionstrategie: Optimierung Technisher Systeme nach prinzipien des Biologishen Evolution. Fromman-Hozlboog Verlag (1973)
Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computation, pp. 71–87. Springer, Berlin (2003)
Caponio, A., Cascella, G.L., Neri, F., Salvatore, N., Sumner, M.: A fast adaptive memetic algorithm for on-line and off-line control design of pmsm drives. IEEE Transactions on System Man and Cybernetics-part B 37, 28–41 (2007)
Neri, F., Toivanen, J., Cascella, G.L., Ong, Y.S.: An adaptive multimeme algorithm for designing HIV multidrug therapies. IEEE/ACM Transactions on Computational Biology and Bioinformatics 4, 264–278 (2007)
Tirronen, V., Neri, F., Kärkkäinen, T., Majava, K., Rossi, T.: An enhanced memetic differential evolution in filter design for defect detection in paper production. Evolutionary Computation 16(4), 529–555 (2008)
Caponio, A., Neri, F., Tirronen, V.: Super-fit control adaptation in memetic differential evolution frameworks. Soft Computing-A Fusion of Foundations, Methodologies and Applications (to appear, 2009)
Smith, J.E.: Coevolving memetic algorithms: A review and progress report. IEEE Transactions on Systems, Man, and Cybernetics, Part B 37, 6–17 (2007)
Zamuda, A., Brest, J., Bošković, B., Žumer, V.: Large scale global optimization using differential evolution with self-adaptation and cooperative co-evolution. In: Proceedings of the IEEE World Congress on Computational Intelligence, pp. 3719–3726 (2008)
Back, T.: Selective pressure in evolutionary algorithms: a characterization of selection mechanisms. In: Proceedings of the IEEE World Congress on Computational Intelligence, vol. 1, pp. 57–62 (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weber, M., Tirronen, V., Neri, F. (2009). Fitness Diversity Parallel Evolution Algorithms in the Turtle Race Game. In: Giacobini, M., et al. Applications of Evolutionary Computing. EvoWorkshops 2009. Lecture Notes in Computer Science, vol 5484. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01129-0_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-01129-0_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01128-3
Online ISBN: 978-3-642-01129-0
eBook Packages: Computer ScienceComputer Science (R0)