gptkbp:instanceOf
|
gptkb:artificial_intelligence
|
gptkbp:architecture
|
gptkb:convolutional_neural_network
|
gptkbp:author
|
Silver, Hubert, Schrittwieser, et al.
|
gptkbp:citation
|
gptkb:science
gptkb:Mastering_Chess_and_Shogi_by_Self-Play_with_a_General_Reinforcement_Learning_Algorithm
gptkb:arXiv
2017
|
gptkbp:countryOfOrigin
|
gptkb:United_Kingdom
|
gptkbp:developedBy
|
gptkb:DeepMind
|
gptkbp:hasResearchCenter
|
gptkb:Julian_Schrittwieser
gptkb:Thomas_Hubert
gptkb:David_Silver
gptkb:Demis_Hassabis
|
gptkbp:hasVideoGame
|
gptkb:Go
chess
shogi
|
https://www.w3.org/2000/01/rdf-schema#label
|
AlphaZero
|
gptkbp:language
|
gptkb:Python
gptkb:C++
|
gptkbp:learnsFrom
|
self-play
|
gptkbp:notableAchievement
|
defeated AlphaGo Zero in Go
defeated Elmo in shogi
defeated Stockfish in chess
|
gptkbp:operatingSystem
|
gptkb:Linux
|
gptkbp:predecessor
|
gptkb:AlphaGo
|
gptkbp:publishedIn
|
gptkb:science
|
gptkbp:releaseDate
|
2017
|
gptkbp:supportsAlgorithm
|
gptkb:reinforcement_learning
Monte Carlo tree search
|
gptkbp:trainingTime
|
less than 24 hours per game
|
gptkbp:website
|
https://deepmind.com/research/highlighted-research/alphazero
|
gptkbp:bfsParent
|
gptkb:DeepMind
gptkb:computer_chess
|
gptkbp:bfsLayer
|
5
|