Statements (28)
Predicate | Object |
---|---|
gptkbp:instanceOf |
artificial intelligence algorithm
|
gptkbp:appliesTo |
gptkb:Go
gptkb:Atari_games gptkb:Shogi Chess |
gptkbp:author |
gptkb:Julian_Schrittwieser
gptkb:Thomas_Hubert gptkb:David_Silver |
gptkbp:category |
gptkb:artificial_intelligence
gptkb:machine_learning gptkb:reinforcement_learning |
gptkbp:citation |
gptkb:Mastering_Atari,_Go,_Chess_and_Shogi_by_Planning_with_a_Learned_Model
2020 10.1038/s41586-020-03051-4 |
gptkbp:compatibleWith |
prior knowledge of environment rules
|
gptkbp:developedBy |
gptkb:DeepMind
|
https://www.w3.org/2000/01/rdf-schema#label |
MuZero
|
gptkbp:introducedIn |
2019
|
gptkbp:notableFor |
learning environment dynamics without prior knowledge
|
gptkbp:predecessor |
gptkb:AlphaZero
gptkb:AlphaGo |
gptkbp:publishedIn |
gptkb:Nature
|
gptkbp:solvedBy |
model-based reinforcement learning
|
gptkbp:uses |
gptkb:Monte_Carlo_Tree_Search
neural networks |
gptkbp:bfsParent |
gptkb:Julian_Schrittwieser
gptkb:DeepMind_Technologies |
gptkbp:bfsLayer |
7
|