AWhat changed
Prediction could be learned incrementally from temporal differences without waiting for a final outcome.
Scientific scope
The 1988 sole-authored paper; not later TD(lambda), Q-learning, control, or all RL convergence.
Evidence
The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The paper proves convergence and optimality only under stated special cases; this record does not transfer those guarantees to all later temporal-difference or reinforcement-learning algorithms.
Contributors
- Richard S. Sutton · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
- Sutton, Learning to Predict by the Methods of Temporal Differences
- Sutton 1988 temporal-difference paper copy
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction