Desenvolvimento de Inteligências Artificiais Baseadas em Planeamento de Monte Carlo Temporal para Videojogos de Ação Furtiva

Abstract

Stealth elements have been present in the gaming industry since 1981 with the release of the first game that required the player to hide and traverse through hiding spots, avoiding lights to achieve a goal. Stealth-based games evolved throughout the years, but the evolution of the game mechanics eventually stopped, becoming only an improvement over past work. This thesis intends to help revitalize the paradigm this kind of games, creating an artificial intelligence that instead of acting as a reactive opponent, has the ability to play a more proactive role in the game world, making it possible for the AI to be a player in the game. To test this AI, a simulator with procedurally generated content centered around stealth elements was created in parallel to the AI's development. This shift in focus will allow the creation of new mechanics and a new meta-game, hopefully driving the creation of a new type of games.