UVU measures value-function uncertainty by the TD-trained prediction error between an online network and a fixed random target, and in the infinite-width NTK limit this error exactly matches ensemble variance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Universal Value-Function Uncertainties
UVU measures value-function uncertainty by the TD-trained prediction error between an online network and a fixed random target, and in the infinite-width NTK limit this error exactly matches ensemble variance.