Algorithm helps AI triumph in legendary Atari game

In 2015, Google's DeepMind AI was tasked with learning to play Atari video games. It was quite successful too, becoming as good at Video Pinball as a human player. But beyond the simple arcade games it began to struggle, notoriously failing to even collect the first key in the legendary 1980s adventure game Montezuma's Revenge, due to the game's complexity. However, a new approach has resulted in an AI algorithm that learnt from mistakes and identified intermediate steps 10 times faster, succeeding where Google failed and successfully autonomously playing Montezuma's Revenge. The work was carried out by Fabio Zambetta and his team from RMIT University in Melbourne, Australia.