2016
David Silver
b. 1976
Reinforcement Learning & AlphaGo
Led research behind AlphaGo, combining deep neural networks with search and reinforcement learning to master the game of Go.
Silver was a lead researcher on DeepMind's AlphaGo system. Its 2016 Nature paper described networks for evaluating positions and selecting moves, combined with tree search; that March, AlphaGo defeated Lee Sedol 4–1.
He subsequently led work on AlphaGo Zero and AlphaZero, which learned through self-play. These systems showed how learning and planning could produce strong strategies without relying on human demonstrations.
Dated contributions
2016
Reinforcement Learning & AlphaGo
David Silver
Led research behind AlphaGo, combining deep neural networks with search and reinforcement learning to master the game of Go.
Paper · 2016 — Mastering the game of Go with deep neural networks and tree search ↗
