A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Abstract

One program to rule them all Computers can beat humans at increasingly complex games, including chess and Go. However, these programs are typically constructed for a particular game, exploiting its properties, such as the symmetries of the board on which it is played. Silver et al. developed a program called AlphaZero, which taught itself to play Go, chess, and shogi (a Japanese version of chess) (see the Editorial, and the Perspective by Campbell). AlphaZero managed to beat state-of-the-art programs specializing in these three games. The ability of AlphaZero to adapt to various game rules is a notable step toward achieving a general game-playing system. Science , this issue p. 1140 ; see also pp. 1087 and 1118

Keywords

Reinforcement learningReinforcementComputer scienceArtificial intelligenceCognitive scienceMachine learningPsychologySocial psychology

Affiliated Institutions

Related Publications

Teaching thinking skills.

Richard J. Hernstein , Raymond S. Nickerson , Margarita de Sánchez +1 more

A course was developed to teach cognitive skills that apply to learning and intellectual performance independently of subject matter, stressing observation and classification, r...

1986 American Psychologist 342 citations

Publication Info

Year: 2018
Type: article
Volume: 362
Issue: 6419
Pages: 1140-1144
Citations: 3322
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

3322

OpenAlex

Cite This

APA Style

                            
                                
                                    David Silver, 
                                
                                    Thomas Hubert, 
                                
                                    Julian Schrittwieser
                                
                                et al.
                            
                            (2018). 
                            A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. 
                            Science
                            , 362
                            (6419)
                            , 1140-1144.
                            https://doi.org/10.1126/science.aar6404
                        

Identifiers

DOI: 10.1126/science.aar6404