RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
Statistics and Computing , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
New expert-informed Bayesian priors and elicitation procedure for inferring single-subject functional connectivity graphs from resting-state fMRI, yielding posterior distributions over edge weights.
citing papers explorer
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
-
Prior elicitation for Bayesian estimation of single-subject connectivity networks
New expert-informed Bayesian priors and elicitation procedure for inferring single-subject functional connectivity graphs from resting-state fMRI, yielding posterior distributions over edge weights.