Using human data to create stronger opponents in Real Time Strategy Games
Artificial Intelligence in Real Time Strategy games is a very challenging research domain. These games often simulate a simplified real-life environment with a set of rules and some goals that the player has to achieve in order to win the game. Nowadays developers encourage players to play against other human players instead of AIs because NPCs are not challenging enough in most of the cases. Industry tends to make game AIs more fun to play against, while academics are trying to develop unbeatable AIs. This PhD project investigates the gap between academic and industrial AIs in RTS games. The research would focus on using human data to create micro and macro strategies in more complex games. Another interesting approach would be to try to create agents without using human data to create stronger opponents.
I graduated from the University of Essex with a BSc Computer Science degree in 2018. My main interest is artificial intelligence and its application to all sort of problems ranging from computer vision to game AI. I like spending my spare time with various activities which mainly involves reading, playing video games and skateboarding.
Home institution: Queen Mary
Supervisor: Dr Diego Perez
Ready to apply?
Once you have identified your potential supervisor, we would encourage you to contact them to discuss your research proposal.Learn More