AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Variance-Reduced Off-Policy TDC Learning: Non-Asymptotic Convergence Analysis

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Variance-reduced policy gradient · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
add variance reduction to TD and TDC (VRTD, VRTDC vs TD, TDC)TD/TDC · Garnet problemasymptotic convergence errorHelped
two time-scale variance reduction (VRTDC) instead of one time-scale (VRTD)VRTD · Garnet problemmean convergence errorHelped
VRTDC vs VRTD across batch sizes M (ablation)VRTD · Garnet problemasymptotic convergence errorHelped
add variance reduction to TDCTDC · Garnet problemvariance of stochastic updates (theta and w)Helped
VRTDC vs VRTDVRTD · Frozen Lakeasymptotic convergence errorHelped
variance reduction on one time-scale only (VRTD) vs TDCTDC · Frozen Lakeasymptotic convergence errorNo clear effect
vary batch size M for VRTDC vs VRTD (ablation)VRTD · Frozen Lakeasymptotic convergence errorHelped
add variance reduction to TDCTDC · Frozen Lakevariance of pseudo-gradient updatesHelped

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