Ronald J. Williams

E248157
computer scientist reinforcement learning algorithm researcher scientific article

Ronald J. Williams is a computer scientist known for his influential contributions to neural networks and machine learning, particularly in the development of backpropagation and reinforcement learning algorithms.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (1)

Label Occurrences
Ronald J. Williams canonical 2

How this entity was disambiguated

Statements (33)

Predicate Object
instanceOf computer scientist ⓘ
reinforcement learning algorithm ⓘ
researcher ⓘ
scientific article ⓘ
appliesTo stochastic neural networks ⓘ
associatedWithConcept gradient-following reinforcement learning ⓘ
stochastic gradient ascent in expected reward ⓘ
author Ronald J. Williams self-linksurface differs ⓘ
coAuthorOf REINFORCE ⓘ
surface form: “Simple statistical gradient-following algorithms for connectionist reinforcement learning”
contributedTo development of policy gradient methods in reinforcement learning ⓘ
theoretical foundations of neural network learning rules ⓘ
understanding of credit assignment in neural networks ⓘ
developed REINFORCE ⓘ
surface form: REINFORCE learning rule
fieldOfWork computer science ⓘ
machine learning ⓘ
neural networks ⓘ
reinforcement learning ⓘ
reinforcement learning ⓘ
hasCitationalImpactOn neural network training methods ⓘ
policy gradient reinforcement learning literature ⓘ
hasGender male ⓘ
hasNotability pioneering work in neural network reinforcement learning ⓘ
hasResearchInterest connectionist models ⓘ
learning algorithms ⓘ
probabilistic neural networks ⓘ
influenced research in deep reinforcement learning ⓘ
research on gradient-based learning in stochastic networks ⓘ
knownFor REINFORCE ⓘ
surface form: REINFORCE algorithm

work on stochastic gradient learning in neural networks ⓘ
notableFor contributions to backpropagation algorithms ⓘ
contributions to reinforcement learning algorithms ⓘ
publicationLanguage English ⓘ
usesMethod backpropagation of error ⓘ

How these facts were elicited

Referenced by (2)

Full triples — surface form annotated when it differs from this entity's canonical label.

“Learning representations by back-propagating errors” → author → Ronald J. Williams ⓘ
subject surface form: Learning representations by back-propagating errors
Ronald J. Williams → author → Ronald J. Williams self-linksurface differs ⓘ
subject surface form: “Simple statistical gradient-following algorithms for connectionist reinforcement learning”