Design of Emergent and Adaptive Virtual Players in a War RTS Game - Foundations on Natural and Artificial Computation - page 380

strategy game (wRTS); to do so, a model to mimic how the human player acts
in the game is first constructed during the game, and further a strategy for a
virtual player is evolved (in between games) via an evolutionary algorithm.
Our proposal was compared with an expert system designed specifically for
the game. Whereas no significance differences have been highlighted in the ex-
periments, we make note that our approach has evident advantages compared to
classical manufactured scripts (i.e., expert systems) used in videogame industry:
for instance, it avoids the predictability of actions to be executed by the virtual
player and thus guarantees to maintain the interest of the player This is specially
interesting when the game involves more than one player as our approach would
allow to construct virtual players adapted particularly to each of the human
players (and this cannot be obtained with a pre-programmed script).
Further research will cope with multi-player games and thus multi-objective
evolutionary programming techniques should be considered.
Acknowledgements. This work is supported by project NEMESIS (TIN-2008-
05941) of the Spanish Ministerio de Ciencia e Innovacion, and project TIC-6083
of Junta de Andalucıa.
References
1. Liden, L.: Artificial stupidity: The art of intentional mistakes. In: AI Game Pro-
gramming Wisdom 2, pp. 41-48. Charles River Media, Inc. (2004)
2. Ahlquist, J.B., Novak, J.: Game Artificial Intelligence. Game Development essen-
tials. Thomson Delmar Learning, Canada (2008)
3. Buro, M.: Call for AI research in RTS games. In: Fu, D., Orkin, J. (eds.) AAAI
workshop on Challenges in Game AI, San Jose, pp. 139-141 (2004)
4. Corruble, V., Madeira, C.A.G., Ramalho, G.: Steps toward building of a good ai for
complex wargame-type simulation games. In: Mehdi, Q.H., Gough, N.E. (eds.) 3rd
International Conference on Intelligent Games and Simulation (GAME-ON 2002),
London, UK (2002)
5. Forbus, K.D., Mahoney, J.V., Dill, K.: How qualitative spatial reasoning can im-
prove strategy game ais. IEEE Intelligent Systems 17(4), 25-30 (2002)
6. Louis, S.J., Miles, C.: Playing to learn: case-injected genetic algorithms for learning
to play computer games. IEEE Trans. Evol. Comput. 9(6), 669-681 (2005)
7. Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-time neuroevolution in the
nero video game. IEEE Trans. Evol. Comput. 9(6), 653-668 (2005)
8. Livingstone, D.: Coevolution in hierarchical ai for strategy games. In: IEEE Sym-
posium on Computational Intelligence and Games (CIG 2005), Essex, UK, IEEE,
Los Alamitos (2005)
9. Miles, C., Louis, S.J.: Co-evolving real-time strategy game playing influence map
trees with genetic algorithms. In:International Congress on Evolutionary Compu-
tation, Portland, Oregon. IEEE press, New York (2006)
10. Lichocki, P., Krawiec, K., Jaskowski, W.: Evolving teams of cooperating agents for
real-time strategy game. In: Giacobini, M., Brabazon, A., Cagnoni, S., Di Caro,
G.A., Ekart, A., Esparcia-Alcazar, A.I., Farooq, M., Fink, A., Machado, P. (eds.)
EvoWorkshops 2009. LNCS, vol. 5484, pp. 333-342. Springer, Heidelberg (2009)