Abstract
Video games have been popular and can be divided into many categories, such as fighting games, real-time strategy, role-playing, etc. For the last decade, game AI has been applied to non-player characters (NPCs) to achieve desired behavior goals. In this study, a model based on Deep Learning was created to predict AI game action. The research question is, "Is it possible to predict the opponent’s action on time? The prediction will enable us to choose a game action to win the opponent. FightingICE platform was chosen to be the testbed. FightingICE is a fighting game platform with API developed for research purposes at Ritsumeikan University that allows custom AI to be inserted. The deep learning model was created using game data from default AI bots in FightingICE speed-running competitions. The result is that the model can predict AI selecting action with 98% accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
