Williams: REINFORCE policy-gradient algorithms

What changed

Derived stochastic weight updates following the gradient of expected reinforcement in the paper's model.

Scientific scope

The record is the sole-author 1992 Machine Learning article. Earlier actor–critic work, Q-learning, later policy-gradient estimators, variance reduction, natural gradients and deep-RL implementations remain separate.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the sole-author 1992 Machine Learning article. Earlier actor–critic work, Q-learning, later policy-gradient estimators, variance reduction, natural gradients and deep-RL implementations remain separate.

Contributors

• Ronald J. Williams · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Springer record for REINFORCE algorithms
• Ronald Williams publication list

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