Score breakdown

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

paper-0033 · paper · 1992

Ronald J. Williams

REINFORCE; the original policy-gradient method.

Academic, score -0.1582

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent7463.00.0335890.50.016795OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.1recorded as missing; penalized by rule, never imputed
readership_persistencepresent15.01.00.050.05OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed

Broad Influence, score 0.2067

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent7463.00.0335890.20.006718OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.125recorded as missing; penalized by rule, never imputed
readership_persistencepresent15.01.00.40.4OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.075recorded as missing; penalized by rule, never imputed

Governance Practitioner, score -0.2166

MetricStatusValueNorm.WeightContributionSourceConfidenceProvenance
citation_countpresent7463.00.0335890.250.008397OpenAlexhighlink
library_holdingsmissingrecorded as missing, penalized by rule, never imputed−0.15recorded as missing; penalized by rule, never imputed
readership_persistencepresent15.01.00.10.1OpenAlexmediumlink
syllabus_adoptionsmissingrecorded as missing, penalized by rule, never imputed−0.175recorded as missing; penalized by rule, never imputed

A rank is not a verdict on intrinsic worth. It is a transparent output of declared evidence, weights, and missing-data rules at a specific release date.

Disagree with this rank or a number? Challenge it with your evidence. Every challenge gets a public identifier and a published resolution.