Back to Projects

AlphaGo / AlphaZero

Archived

DeepMind's Go AI that achieved superhuman level through self-play

Visit Website

Project Information

Category:Gaming
Released:2016
Developer:Google DeepMind
License:Proprietary
gaminggoself-play

About

AlphaGo defeated world champion Lee Sedol 4:1 in 2016. AlphaZero further evolved, achieving superhuman level in Go, chess, and shogi through pure self-play (no human game data). Its self-play methodology became the foundational idea for all multi-agent adversarial systems.

Related Projects