1998

Sutton RL textbook published

Richard Sutton and Andrew Barto published reinforcement learningTraining agents by reward and penalty signals — used in games, robotics, and recommendation systems.: An Introduction in 1998 — the foundational textbook for RL theory and practice.

What it was for

Richard S. SuttonSutton's temporal-difference learning and policy-gradient frameworks became the vocabulary for game-playing agents, roboticsMachines that sense, plan, and act in the physical world — from factory arms to Mars rovers., and later DeepMind's AlphaGo. The book's second edition in 2018 updated decades of RL progress.

People

  • Rich Suttonauthor

Why it's here

Sutton's textbook codified reinforcement learningTraining agents by reward and penalty signals — used in games, robotics, and recommendation systems. as a teachable discipline.

Why it mattered

It trained researchers who built modern game-playing and roboticsMachines that sense, plan, and act in the physical world — from factory arms to Mars rovers. AI.

What it solved

RL ideas were scattered across papers without a unified pedagogical framework.

Media

  • Richard S. Sutton
    ImageRichard S. Sutton

    Xuthoria, CC BY-SA 4.0, via Wikimedia Commons

Related