In recent years the video game industry has experienced rapid expansion developing virtual environments that accurately mimic a real-world setting. However, the industry almost entirely relies on finite state machines for deploying computer-controlled characters within these environments. This has resulted in simulated inhabitants that lack the same degree of believability as their surroundings. As part of this research a simulation was developed using Java in which an agent was placed. In a survey students were asked to rank the believability of different artificial intelligence techniques employed by the simulation. The genetic algorithm developed for this simulation provided for an agent whose decisions were more believable than the decisions generated by a finite state machine or random selection process.
© 2010 by the Consortium for Computing Sciences in Colleges.