David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan et Demis Hassabis, « A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play », Science, vol. 362, no 6419, , p. 1140–1144 (DOI10.1126/science.aar6404)