GAIG Game AI Research Group @ QMUL

Ivan Bravi

Research topic: Game-Analyzing AI Agents

Ivan Bravi has obtained his B.Sc and M.Sc in Engineering of Computer Systems at the Politecnico di Milano, Italy. From January to July 2016 he was Visiting Scholar at the NYU’s Game Innovation Lab in New York where, under the supervision of Prof. Julian Togelius, he did research in the field of general videogame playing. Currently his main interests are Artificial General Intelligence and games.

PhD Defense

Ivan’s thesis investigates automated play-testing of games using a number of optimised statistical forward planning algorithms. The examiners, Dr Chris Child from City University, and Prof Massimo Poesio from Queen Mary University of London, were impressed by the novel contributions of the work and the thorough and insightful experimental evaluations. Among other things Ivan introduced the use of event-value functions and showed how these lead to more diverse and expressive agent behaviours compared to more conventional state-value functions. During his PhD Ivan published many papers in venues including IEEE Transactions on Game, IEEE Conference on Games, and Genetic and Evolutionary Computation Conference (GECCO).

Ivan was funded by the wonderful IGGI CDT (EPSRC) and is currently with the Danish Game AI startup

GAIG Publications