Intelligent Agent Applied in Digital Games

• Patrick P. Rodrigues UNIFTEC
• João L. T. da Silva UNIFTEC

DOI: https://doi.org/10.5753/wesaac.2018.33271

Abstract

Currently the area of Digital Games tends to offer more and more realism and immersiveness, promoting a better experience to the player. Along with this the player expects an increasingly natural behavior of NPCs (Non-Player Character), looking for a more natural adaptation of the NPC’s interactions in the context of the game. In this sense, Artificial Intelligence, in its area of Multiagent Systems, offers a promising technology to implement intelligent cognitive NPCs. However, specific features in game engines such as real-time, synchronization and communication aspects are not easily supported in terms of multiagent platforms, making it difficult to fully integrate AI techniques in this context. On the other hand, the agent autonomy feature may offer benefits for more convincing gameplay, and even for serious games, for instance. In this article, we focus on modeling a decisional component in an NPC agent to define an intelligent behavior of the NPC, which is adaptive according to the specific playing of each player. We intend, with these initial ideas and prototypes, to experiment the concept of intelligent agents applied to the area of digital games, using an artificial neural network as a decisional component.

References

Fogel, D. B., Hays, T. J., and Johnson, D. R. (2004). A platform for evolving characters in competitive games. In Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753), volume 2, pages 1420–1426 Vol.2.

Leyton-Brown, K. and Shoham, Y. (2008). Essentials of Game Theory: A Concise, Multidisciplinary Introduction. Morgan and Claypool Publishers, 1st edition.

Miikkulainen, R. (2006). Creating intelligent agents in games. The Bridge, pages 5–13.

Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., and Hassabis, D. (2016). Mastering the game of go with deep neural networks and tree search. Nature, 529:484–503.

Spronck, P., Sprinkhuizen-kuyper, I., and Postma, E. (2003). Online adaptation of game opponent ai in simulation and in practice. In In Proceedings of the Fourth International Conference on Intelligent Games and Simulation, pages 93–100.