A Neuroevolution Approach to Imitating Human-Like Play in Ms. Pac-Man Video Game Maximiliano Miranda, Antonio A. S´ anchez-Ruiz, and Federico Peinado Departamento de Ingenier´ ıa del Software e Inteligencia Artificial Universidad Complutense de Madrid c/ Profesor Jos´ e Garc´ ıa Santesmases 9, 28040 Madrid (Spain) m.miranda@ucm.es - antsanch@ucm.es - email@federicopeinado.com http://www.narratech.com Abstract. Simulating human behaviour when playing computer games has been recently proposed as a challenge for researchers on Artificial Intelligence. As part of our exploration of approaches that perform well both in terms of the instrumental similarity measure and the phenomeno- logical evaluation by human spectators, we are developing virtual players using Neuroevolution. This is a form of Machine Learning that employs Evolutionary Algorithms to train Artificial Neural Networks by consider- ing the weights of these networks as chromosomes for the application of genetic algorithms. Results strongly depend on the fitness function that is used, which tries to characterise the human-likeness of a machine- controlled player. Designing this function is complex and it must be implemented for specific games. In this work we use the classic game Ms. Pac-Man as an scenario for comparing two different methodologies. The first one uses raw data extracted directly from human traces, i.e. the set of movements executed by a real player and their corresponding time stamps. The second methodology adds more elaborated game-level parameters as the final score, the average distance to the closest ghost, and the number of changes in the player’s route. We assess the impor- tance of these features for imitating human-like play, aiming to obtain findings that would be useful for many other games. Keywords: Virtual Video Game Player, Human Behaviour Imitation, Artificial Neural Networks, Evolutionary Computing, Genetic Algorithms, Machine Learning, Artificial Intelligence 1 Introduction Researchers on Artificial Intelligence (AI) are always looking for problems that are challenging but feasible at the same time, in order to progress their mission of computationally recreating intelligence. Imitating video game players has been recently considered an interesting challenge for the AI research community. Ex- amples of this trend are the competitions regarding the development of believable video game characters that have taken place during the last years [5,12].