Mastering the game of Go with deep neural networks and tree search.
David SilverAja HuangChris J. MaddisonArthur GuezLaurent SifreGeorge van den DriesscheJulian SchrittwieserIoannis AntonoglouVedavyas PanneershelvamMarc LanctotSander DielemanDominik GreweJohn NhamNal KalchbrennerIlya SutskeverTimothy P. LillicrapMadeleine LeachKoray KavukcuogluThore GraepelDemis HassabisPublished in: Nat. (2016)
Keyphrases
- tree search
- game tree search
- neural network
- game tree
- board game
- constraint propagation
- branch and bound
- alpha beta
- search algorithm
- search tree
- mathematical programming
- iterative deepening
- path finding
- tree search algorithm
- state space
- game playing
- imperfect information
- artificial neural networks
- search space
- branch and bound algorithm
- coverage includes
- nash equilibrium
- game theory
- game play
- game theoretic
- metaheuristic
- monte carlo
- lower bound
- nearest neighbor
- database design
- computer games
- temporal constraints
- video games
- associative memory