An application of genetic algorithm based on abstract data type for the problem of generation of scenarios for electronic games

摘要

As game users' demand for games with more realistic behavior ascends, so does the importance of artificial intelligence techniques in video games. Among the game genres, RPG (specially the MMORP variety) stands as an excellent test bed for applying such techniques as it provides a rich environment with interesting events happing simultaneously, akin to the real world. Using a MMORPG as background, this paper demonstrates the use of an evolutionary approach called genetic algorithm based on abstract data types (GAADT), for managing the dynamics of geophysics events in a MMORPG environment, asserting that specific events will occur only in areas where they are prone to. In addition, as GAADT is an algorithm for random optimization, it fits the criteria of unexpected occurrences in arbitrary locations, better simulating a real world environment and presenting the game environment geographic characteristics as an extra factor to be considered by the society of players.