Co-operative General Game Playing
My chosen field of research is Co-operative General Game Playing. This is a combination of the traditional field of Co-operative Artificial Intelligence (AI) and that of General Game Playing (GGP).
GGP is finding applications in industry games due to its inherent resistance to game changes saving programmer time. In traditional AI development, a simple change such as the amount of damage that a single rifle does can require a change in the AI in order to ensure that it is still choosing the optimum strategy. Such a small change might not require a rethink for the AI but if a particular gun were removed - some AI rules might need changing such as a rule to attempt to find that gun in the environment. GGP wouldn't require a change, as the simulations would simply not encounter the gun.
Co-operative AI is a powerful technique that can be used for more realistic looking AI as well as more capable AI in games. A final benefit that most interests me is the potential for co-operative AI to provide engaging experiences with direct co-operation between human and AI players.
The combination of the two would allow AI that doesn't need retuning during development and can directly work with the user to bring single play closer to the online experience. Online play is often considered more engaging due to the variety of people that you play with as well as the often vastly superior intelligence. Getting single player modes of games nearer this experience would be a large selling point for a computer game.
Piers recently graduated from the University of Essex with an MSc in Computer Science. His interests lie in the field of Artificial Intelligence and in particular Multi-Agent Systems.
Home institution: Essex
Ready to apply?
Once you have identified your potential supervisor, we would encourage you to contact them to discuss your research proposal.Learn More