In this video, an AI uses Machine Learning (Reinforcement Learning) to play the Mario Kart Wii time trials on Luigi Circuit, playing as Funky Kong with the Bowser Bike / Flame Runner, using just pixel input.
To give some technical details, this uses Rainbow DQN https://arxiv.org/abs/1710.02298?context=cs. All parameters are the same as in the original paper, except for sigma (for noisy nets) which was set to 0.1 instead of 0.5.
source