Abstract
This paper presents the intelligent game agent that gives effective intelligence to NPCs (Non Player Characters) for which intelligence did not exist. Generally, non-player characters (NPCs), or agents, such as monsters, enemy guards, or friendly wingmen, can be controlled by a finite-state machine. To overcome the shortcoming of NPC’s restricted action, we applied a LSVM (Linear Support Vector Machine) as pattern recognition for the intelligent game agent, and processed all data in XML format to handle the data efficiently. The intelligent agent is executed in the base of the game physics engine. A lot of NPCs that act in a game learn physics values that are produced in the game, and change NPS’s action intelligently. We applied two pattern recognition algorithms to estimate the algorithm’s performance through comparison. As indicated by experiments, when the M-BP has a fixed number of input layers (number of physical parameters) and output layers (impact value), it shows the best performance when the number of hidden layers is 3 and the learning count number is 30,000. The pattern recognizer that applied LSVM shows the best performance when the learning count number is 25000, and the LSVM shows better performance than the M-BP in the intelligent game agent.
This study was supported by a grant of the Seoul R&BD Program.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
DFC Intelligence (2002-2004), http://www.dfcint.com
Kook, H.J., Novak Jr., G.S.: Representation of models for solving real world physics problems. In: Proceedings of the Sixth Conference on Artificial Intelligence for Applications, pp. 274–280 (1990)
Cass, S.: Mind games. Spectrum. IEEE. 39(12), 40–44 (2002)
Math Engine.: http://www.mathengine.com
Havok.: http://havok.com
Meqon.: http://www.meqon.com
Open Dynamics Engine.: http://ode.org
Lawlor, O.S., Kalee, L.V.: A Voxel-based Parallel Collision Detection Algorithm. In: Proceedings of the 6th international conference on Supercomputing, June 2002, pp. 285–293 (2002)
Zachmann, G.: Minimal Hierarchical Collision Detection. In: Proceedings of the ACM symposium on Virtual reality software and technology, November 2002 (2002)
DirectIA.: http://www.masa-sci.com/
Spark.: http://www.louderthanabomb.com/
Memetic.: http://www.memeticai.org/
Renderware AI SDK.: http://www.renderware.com/
Tang, W., Wan, T.R.: Intelligent self-learning characters for computer games. In: Proceedings of Eurographics UK Conference 2002, pp. 51–58 (2002)
Hui, Y.C., Prakash, E.C., Chaudhari, N.S.: Game AI: Artificial intelligence for 3D path finding. In: TENCON 2004. 2004 IEEE Region 10 Conference, vol. B, pp. 306–309 (2004)
Cant, R., Churchill, J., Al-Dabass, D.: A hybrid artificial intelligence approach with application to games. In: Neural Networks. Proceedings of the 2002 International Joint Conference on, vol. 2, pp. 1575–1580 (2002)
Phansalkar, V.V., Sastry, P.S.: Analysis of the back-propagation algorithm with momen-tum. Nerual Networks. IEEE transaction on, 505–506 (1994)
Burges, C.J.C.: A tutorial on support vector machines for pattern recognition. Data Mining Knowl, Disc 2(2), 1–47 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Choi, J., shin, D., Shin, D. (2006). Intelligent Game Agent Based Physics Engine for Intelligent Non Player Characters. In: Shi, ZZ., Sadananda, R. (eds) Agent Computing and Multi-Agent Systems. PRIMA 2006. Lecture Notes in Computer Science(), vol 4088. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11802372_42
Download citation
DOI: https://doi.org/10.1007/11802372_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-36707-9
Online ISBN: 978-3-540-36860-1
eBook Packages: Computer ScienceComputer Science (R0)