Genetic Algorithm in Survival Shooter Games NPCs

Alisson Steffens Henrique, Ricardo Martins Brasil Soares, Rudimar Luis Scaranto Dazzi, Rodrigo Lyra


Games must engage players by keeping them in the game flow. To
better define the game difficulty according to the player, Genetic
Algorithms can be used. One of the interesting characteristics of
Genetic Algorithm is that it is a non-deterministic algorithm. For the
player’s vision, it means that enemies are unpredictable. By not
knowing which NPCs he will face, the gameplay turns more
interesting. Another amusing factor for gaming is its adaptability,
causing NPCs to slowly struggle to find a way to beat the player. These
two characteristics make Genetic Algorithms good tools to make
games more entertaining. This paper aims to demonstrate this
adaptation capability in the Survival Shooter, developed by Unity
enterprise and modified by the author for the algorithm
implementation. As result, it shows that players could stay in the game
flow while playing against genetically modified enemies.

Texto completo:




  • Não há apontamentos.