Mastering the Game of Go (AlphaGo/AlphaZero)

Editorial record

Plain-language summary

AlphaGo paired a policy network (which moves to consider) and a value network (who is winning) with tree search to defeat top human Go players. AlphaZero simplified this into a single network trained purely by playing against itself, guided by search, and generalized to chess and shogi. The work showed that self-play plus search could reach superhuman strength without human examples or handcrafted evaluation.