Pareto Ensembles for Evolutionary Synthesis of Neurocontrollers in a 2D Maze-Based Video Game

Abstract:

In this paper, we present a study of evolving artificial neural network controllers for autonomously playing maze-based video game. A system using multi-objective evolutionary algorithm is developed, which is called as Pareto Archived Evolution Strategy Neural Network (PAESNet), with the attempt to find a set of Pareto optimal solutions by simultaneously optimizing two conflicting objectives. The experiments are designed to address two research aims investigating: (1) evolving weights (including biases) of the connections between the neurons and structure of the network through multi-objective evolutionary algorithm in order to reduce its runtime operation and complexity, (2) improving the generalization ability of the networks by using neural network ensemble model. A comparative analysis between the single network model as the baseline system and the model built based on the neural ensemble are presented. The evidence from this study suggests that Pareto multi-objective paradigm and neural network ensembles can be effective for creating and controlling the behaviors of video game characters.

• Periodical: Applied Mechanics and Materials (Volumes 284-287)
• Pages: 3173-3177
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.284-287.3173
• Online since: January 2013
• Authors: Tse Guan Tan, Jason Teo, Kim On Chin, Patricia Anthony
• Keywords: Intelligent Computing, Multi-Objective Evolutionary Algorithm, Neural Network Ensemble

References

[1] D.P. Niu, F.L. Wang, L.L. Zhang, D.K. He and M.X. Jia: Chemometr. Intell. Lab. Vol. 105 (2011), p.125.

[2] I. Millington and J. Funge: Artificial Intelligence for Games (Morgan Kaufmann, Massachusetts 2009).

[3] Information on http: /www. msnbc. msn. com/id/3131181.

[4] J.B. Ahlquist and J. Novak: Game Development Essentials: Game Artificial Intelligence (Thomson Delmar Learning, New York 2008).

[5] J.D. Knowles and D.W. Corne: Proc. of the Congress on Evolutionary Computation (1999), p.98.

[6] K. Baldauf and R.M. Stair: Succeeding with Technology: Computer Concepts for Your Life (Course Technology Cengage Learning, Massachusetts 2011).

[7] K. Deb: Multi-Objective Optimization Using Evolutionary Algorithms (John Wiley and Sons, New York 2001).

[8] L. Yu, S. Wang and K.K. Lai: Expert Syst. Appl. Vol. 34 (2008), p.1434.

[9] L.K. Hansen and P. Salamon: IEEE Trans. Pattern Anal. Mach. Intell. Vol. 12 (1990), p.993.

[10] S. Araghinejad, M. Azmi and M. Kholghi: J. Hydrol. Vol. 407 (2011), p.94.

[11] S. Haykin: Neural Networks and Learning Machines (Prentice Hall, New York 2009).

[12] S.M. Lucas: Proc. of the IEEE Symposium on Computational Intelligence and Games (2005), p.203.

[13] Y.B. Tian, S.L. Zhang and J.Y. Li: Int. J. Numer. Model. El. Vol. 24 (2011), p.77.