Skip to content
conftrace_

score-aware gradient estimator

1 paper

Explore in graph

Also known as

SAGE

Co-occurring keywords · papers mentioning both

local lyapunov stability (1) average-reward reinforcement learning (1) stochastic gradient ascent (1) regret bound (1) stationary distribution (1) exponential family (1) markov decision process (1) policy gradient (1) reinforcement learning (1)

Papers

Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability JMLR 2025