2017 ⟶ AlphaGo Zero Achieves Superhuman Go Performance
Google DeepMind revealed that AlphaGo Zero—an improved versi...
Year
2015
2016
2017
2019
♟️ AlphaGo Defeats Lee Sedol in Go
🧠 AlphaGo Zero Achieves Superhuman Go Performance
Google DeepMind revealed that AlphaGo Zero—an improved version of AlphaGo—displayed significant performance gains while using far fewer tensor processing units (as compared to AlphaGo Lee; it used same amount of TPU's as AlphaGo Master). Unlike previous versions, which learned the game by observing millions of human moves, AlphaGo Zero learned by playing only against itself. The system then defeated AlphaGo Lee 100 games to zero, and defeated AlphaGo Master 89 to 11. Although unsupervised learning is a step forward, much has yet to be learned about general intelligence. AlphaZero masters chess in four hours, defeating the best chess engine, StockFish 8. AlphaZero won 28 out of 100 games, and the remaining 72 games ended in a draw.⟶
DeepMindAlphaGoAlphaGo ZeroGoSelf-PlayReinforcement LearningGame PlayingArtificial IntelligenceMachine LearningUnsupervised Learning
♠️ DeepStack and Libratus Beat Human Players in Poker
Deepstack is the first published algorithm to beat human players in Imperfect information games, as shown with statistical significance on heads-up no-limit Poker. Soon after, the Poker AI Libratus by different research group individually defeated each of its four-human opponents—among the best players in the world—at an exceptionally high aggregated winrate, over a statistically significant sample. In contrast to Chess and Go, Poker is an Imperfect information game.⟶
PokerImperfect Information GamesGame PlayingArtificial IntelligenceMachine LearningDeepStackLibratus
Canada
United States🥇 AlphaGo Master Defeats Ke Jie in Go
In May 2017, Google DeepMind's AlphaGo (version: Master) beat Ke Jie, who at the time continuously held the world No. 1 ranking for two years, winning each game in a three-game match during the Future of Go Summit.⟶
DeepMindAlphaGoGoGame PlayingArtificial IntelligenceMachine LearningKe JieComputer Games
China🕹️ AlphaStar Reaches Grandmaster Level in StarCraft II
DeepMind's AlphaStar reaches Grandmaster level at StarCraft II, outperforming 99.8 percent of human players.⟶
DeepMindAlphaStarStarCraft IIGame PlayingArtificial IntelligenceMachine LearningReinforcement LearningComputer GamesEsports