1988
Richard Sutton
b. 1957
Temporal-Difference Learning
Developed a foundational account of learning predictions from successive experience, central to reinforcement learning.
His sole-authored 1988 paper, Learning to Predict by the Methods of Temporal Differences, explained how predictions can be updated using other learned predictions rather than waiting for a final outcome.
Earlier work with Andrew Barto and Charles Anderson explored adaptive control. Sutton and Barto later co-authored Reinforcement Learning: An Introduction, first published in 1998.
Dated contributions
1988
Temporal-Difference Learning
Richard Sutton
Developed a foundational account of learning predictions from successive experience, central to reinforcement learning.
Paper · 1988 — Learning to Predict by the Methods of Temporal Differences ↗1998
Reinforcement Learning: An Introduction
Richard Sutton & Andrew Barto
A shared account of learning through interaction helps establish the field's foundations.
Book · 1998 — Reinforcement Learning: An Introduction ↗
Reference
Original work & historical records
- 1988 · Paper — Learning to Predict by the Methods of Temporal Differences ↗
- 1998 · Book — Reinforcement Learning: An Introduction ↗
