Scientific originatorTraining-method researcher
Ronald J. Williams
Also published as Ronald Williams.
Introduced REINFORCE, the policy-gradient method underlying much of reinforcement learning for sequences.
Works in the archive (2) · lead author on 1
- Backpropagation (Learning representations by back-propagating errors) · 1986
- LeadSimple Statistical Gradient-Following Algorithms (REINFORCE) · 1992
“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.