← Back to all news
arXiv AI By Leonardo Cesani, Matteo Papini, Marcello Restelli

Variance-Reduced Policy Gradient is Nearly Minimax-Optimal

Read the original on arXiv AI →

The paper introduces Loopless Variance-Reduced Policy Gradient (LVR-PG), a framework that unifies first‑order estimators combining recursive updates with defensive importance sampling, such as PAGE-PG and STORM-PG. It proves that LVR-PG achieves a ∫O(ε⁻²) last‑iterate global convergence rate under weak gradient domination for general parametric policies, using only first‑order updates and minimal assumptions. By extending lower bounds to continuous parametric policies, the authors show an Ω(ε⁻²) sample complexity limit, establishing that LVR-PG is minimax‑optimal up to logarithmic factors and horizon terms.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 23

Tight Sample Complexity Bounds for Entropic Best Policy Identification

The paper investigates best‑policy identification in finite‑horizon, risk‑sensitive reinforcement learning using the entropic risk measure. It identifies a gap between known lower bounds ≥ η(e^{|eta|H}) and upper bounds ≤ O(e^{2|eta|H}) for sample complexity, attributing the excess factor to loose concentration bounds for exponential utilities. By employing a forward‑model algorithm with KL‑based exploration bonuses and a novel stopping rule, the authors achieve a sample complexity that matches the lower bound, closing the previously open exponential gap.

By Amer Essakine, Claire Vernade
reinforcement-learningbenchmarks
More like this →
arXiv Machine Learning
Oct 2

Fast Regularized Policy Mirror Descent with One-Step TD Updates

The paper introduces Fast Regularized Policy Mirror Descent (PMD) that pairs policy updates with a single temporal-difference (TD) critic step. It proves global linear convergence for finite discounted MDPs using exact coordinate-wise Bellman updates and any positive actor stepsize, regardless of critic initialization. For stochastic TD-PMD with strongly convex mirror maps, the authors achieve an expected value gap of ε after “~O(1/((1-γ)^5 σ_b ε))” transitions, without requiring trajectory resets, generative models, or nested policy evaluation loops.

By Qipei Chen, Wenye Li, Yule Sun, Ke Wei
reinforcement-learning
More like this →