Improving Dynamic Scripting for Adaptive Game AI with a Tactic Replacement Algorithm
Lucas Izumi De Oliveira, Cristiano Grijó Pitangui, Alessandro Vivas Andrade, Luciana Pereira De Assis, Cristiano M. Silva · 2018
Artificial Intelligence (AI) plays an important role in digital games nowadays. With players becoming increasingly demanding, it is vital to provide an AI that challenges and entertains them. The use of Adaptive Artificial Intelligence (AAI) has shown potential to adapt to each player by learning their techniques and offering a consistent challenge. This research consists on the analysis of an AAI technique known as Dynamic Scripting (DS) and in the development of a new algorithm (called Tactic Replacement) to improve it. Results show that, in comparison with the default DS algorithm, the proposed algorithm achieved a time reduction of ≈ 50% to achieve convergence. Also, it was able to reduce by 40% the average number of rounds to reach the convergence.