AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator

Haoyu Han, Heng Yang

ICML 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Variance-reduced policy gradients · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
decrease policy covariance sigma^2 relative to initial-state covariance (sigma0 >> sigma) (ablation)REINFORCE estimator, one-step LQG · double integrator, one-step LQGnoise-to-signal ratioHurt
policy approaches the optimum during optimizationREINFORCE with GD, SGD, Adam · double integrator LQG, T = 30noise-to-signal ratioHurt
use SGD or Adam instead of exact gradient descent (ablation)REINFORCE policy optimization · double integrator LQGconvergence stabilityHurt
stable versus unstable closed-loop dynamics as horizon T grows (ablation)REINFORCE variance · four 2D linear systems with varying spectral radius rho(F)variance: rho(F)=0.912 bounded; rho(F)=1.000 polynomial growth; rho(F)=1.118 exponential growthHurt
smaller batch size and larger learning rate (ablation)REINFORCE with Adam · quadratic polynomial systempolicy collapseHurt
use larger batch size (ablation)REINFORCE with Adam · quadratic polynomial systempolicy collapseMixed
use exact gradient instead of sampled gradient (ablation)REINFORCE with Adam · quadratic polynomial systempolicy collapseImproved
approach optimum with MLP policiesREINFORCE with Adam · LQR and Pendulum with MLP policynoise-to-signal ratioHurt
same trend in MuJoCo environmentsREINFORCE · Hopper and HalfCheetahNSR and objective fluctuationsHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy