Developing Agents with Human Gameplay
Artificial Intelligence has been widely used in video games as agents for non-player characters. This has compelled many researchers to develop and study algorithms and techniques to create agents to compete against humans and defeat them or simply aid them in several tasks. But some have opted for creating agents that have tried to pass the Turing test rather than simply winning. This means deceiving the player into thinking he/she is playing against another human and not a machine. This research has also been focused on a single specific game but not General Video Game Playing (GVGP). This paradigm is being tackled by the General Video Game AI (GVGAI) framework which consists on creating generic agents which are capable of adapting to any game without being given full information on rules and possibly environments. For this proposal, there would be an attempt at combining these concepts into one: developing an agent which would learn from any game given and rather than focusing on winning it would focus on playing in the most humanly way possible, to be believable. This could also develop into the use of emotions in characters, to be more precise, use of facial expressions and communication through other software development kits (SDK).
The believability of agents is significant in video games with many believing it is essential for a better gameplay and, in my personal opinion, central to immersion in the game. Human-like behaviour in general AI, meaning adaptable to any sort of game, is little explored and both this and, possibly, more natural use of expressions and emotions, if successful, it could benefit the games industry in delivering better games with believable characters that would satisfy players even more. This study could also support the expansion on existing research of what makes an agent believable and this could be beneficial to other computation areas besides games such as robotics.
Born in Porto (Portugal) and living in London (UK). I am currently a PhD student in Intelligent Games and Games Intelligence at Queen Mary University of London, with a finished BSc in Computer Games at the University of Essex.
Developed a passion for the games industry ever since one of the very first Game Boy Color handheld consoles was placed in my hands and I have spent countless hours playing games since.
Home institution: Queen Mary
Ready to apply?
Once you have identified your potential supervisor, we would encourage you to contact them to discuss your research proposal.Learn More