Mastering the game of Go with deep neural networks and tree search
David Silver and colleagues published Mastering the game of Go with deep neural networks and tree search online in Nature on January 27, 2016. The paper described AlphaGo, combining policy and value neural networks with Monte Carlo tree search, and reported that the system defeated European Go champion Fan Hui by five games to zero.
Historical classification
This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.
Why it matters
A documented reinforcement-learning and game-playing milestone in which a deep-neural-network system defeated a professional Go player in full-sized Go.
People, organizations & technologies
PEOPLE
David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis
ORGANIZATIONS
Google DeepMind, Google
TECHNOLOGIES
AlphaGo, Policy networks, Value networks, Monte Carlo tree search, Reinforcement learning
Evidence & verification
STATE
verified
CONFIDENCE
high
LAST VERIFIED
2026-09-08T07:46:44+08:00
Nature's article record establishes the title, authors, online publication date of January 27 2016, AlphaGo's policy/value-network and tree-search approach, and the reported 5-0 match result against European Go champion Fan Hui. Google Research independently preserves the publication and abstract. The record is a publication milestone; it does not infer a separate system-birth date or causal relationship to later systems.
Sources
Mastering the game of Go with deep neural networks and tree search
Nature
PUBLISHED
2016-01-27
Mastering the game of Go with deep neural networks and tree search
Google Research
Trace the chronology
Record identity
LINEAiGE IDalphago-2016