Pitt Researcher Uses Video Games to Unlock New Levels of AI

A University of Pennsylvania computer scientists designs algorithms that learn decision strategies in complex and uncertain environments, and tests them in the simulated environments of Multiplayer Online Battle Arena games. The University of Pittsburgh's Daniel Jiang has developed algorithms that learn decision strategies in complex and uncertain environments, and tests them on a genre of video games called Multiplayer Online Battle Arena (MOBA). MOBAs involve players controlling one of several "hero" characters in order to destroy opponents' bases while protecting their own. A successful algorithm for training a gameplay artificial intelligence system must overcome several challenges, like real-time decision making and long decision horizons. Jiang's team designed the algorithm to evaluate 41 pieces of information and output one of 22 different actions; the most successful player used the Monte Carlo tree search method to generate data, which was fed into a neural network.