Move over AlphaGo: AlphaZero taught itself to play three different games

#DeepMind's new #AI is worthy successor to the first program to beat a human at #Go. [Read More]

Summary… * Machine-Made


Dubbed #AlphaZero, this program taught itself to play three different board games (chess, #Go, and shogi, a Japanese form of chess) in just three days, with no human intervention.
"Starting from totally random play, #AlphaZero gradually learns what good play looks like and forms its own evaluations about the game," said Demis Hassabis, CEO and co-founder of #DeepMind.
By playing itself over and over again, AlphaGo Zero (AGZ) trained itself to play #Go from scratch in just three days and soundly defeated the original AlphaGo 100 games to 0.
AGZ only needed to play 4.9 million games to master #Go, compared to 30 million games for its predecessor.
#AlphaZero generalizes this reinforced-learning approach to three different games: #Go, chess, and shogi, a Japanese version of chess.

Opinion… * Man-Made


#Google #DeepMind’s #AlphaZero taught itself to play #Chess, #Go, and #Shoji (a Japanese form of chess) in just three days, with no human intervention. #AI #Trend

Source: Arstechnica