AlphaZero learns chess and shogi from the rules alone

DeepMind posted a paper describing AlphaZero, one algorithm that, given only the rules, reached superhuman play at chess, shogi and Go within 24 hours of self-play training and beat the reigning computer champion program in each game.

Why it mattered It showed the AlphaGo Zero method was not particular to Go but a general way of learning perfect-information games from nothing but their rules.