A Hybrid Fuzzy ANN System for Agent Adaptation in a First Person Shooter

The aim of developing an agent, that is able to adapt its actions in response to their effectiveness within the game, provides the basis for the research presented in this paper. It investigates how adaptation can be applied through the use of a hybrid of AI technologies. The system developed uses the predefined behaviours of a finite-state machine and fuzzy logic system combined with the learning capabilities of a neural computing. The system adapts specific behaviours that are central to the performance of the bot (a computer-controlled player that simulates a human opponent) in the game, with the paper’s main focus being on that of the weapon selection behaviour; selecting the best weapon for the current situation. As a development platform, the project makes use of the Quake 3 Arena engine, modifying the original bot AI to integrate the adaptive technologies