In a paper published by DeepMind, a team of scientists from Alphabet’s UK-based research division has claimed that Agent57 – the first deep reinforcement learning agent – has outperformed humans on all 57 Atari 2600 games in the Arcade Learning Environment data set.  Agent57 combines an algorithm to efficiently explore a meta controller which adapts…

The post How DeepMind’s Agent57 Outperformed Humans In 57 Atari Games appeared first on Analytics India Magazine.