Artificial intelligence · 1992

TD-Gammon

A neural network teaches itself backgammon to world-class level through self-play.

Gerald Tesauro's TD-Gammon learned from 1.5 million self-play games using temporal-difference learning. It reached near-champion strength and changed how human experts play some opening moves, an early glimpse of AlphaGo.

See it in the living tree Wikipedia

Arcs above join it to what it stood on, arcs below to what it led to. The bar places this stretch on the tree's whole timeline.

What it built on 2

Temporal-difference learning 1988
Backpropagation 1986

Related measurements

The dashed line marks when it first worked.

Training compute of notable AI models Source: Epoch AI, Notable AI Models (CC BY 4.0)

Computation per constant dollar, 1850-2006 Latest: 7.3B million units of computer power per 2006 $ (2003) Source: Nordhaus 2007, Two Centuries of Productivity Growth in Computing, J. Econ. Hist. 67(1), Table 6