Learning a Super Mario controller from examples of human play

Imitating human-like behaviour in action games is a challenging but intriguing task in Artificial Intelligence research, with various strategies being employed to solve the human-like imitation problem. In this research we consider learning human-like behaviour via Markov decision processes without being explicitly given a reward function, and learning to perform the task by observing expert´s demonstration. Individual players often have characteristic styles when playing the game, and this method attempts to find the behaviours which make them unique. During play sessions of Super Mario we calculate player´s behaviour policies and reward functions by applying inverse reinforcement learning to the player´s actions in game. We conduct an online questionnaire which displays two video clips, where one is played by a human expert and the other is played by the designed controller based on the player´s policy. We demonstrate that by using apprenticeship learning via Inverse Reinforcement Learning, we are able to get an optimal policy which yields performance close to that of an human expert playing the game, at least under specific conditions.