Research map / Optimization / Nonconvex and smooth optimization
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace double-loop outer loop with probabilistic switch between full-batch and recursive update (PAGE-PG) | REINFORCE-type policy gradient · theory | sample complexity to epsilon-stationary | No clear effect |
| loopless probabilistic switching instead of STORM-style momentum | PAGE-PG · Cartpole | episodes to optimal policy | Mixed |
| use of importance weighting with small step-sizes to enforce bounded weight variance | variance-reduced policy gradient methods · Acrobot | convergence speed | Hurt |
Closest papers by meaning
- On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method (NeurIPS 2021 · similarity 0.91)
- Sample Efficient Policy Gradient Methods with Recursive Variance Reduction (ICLR 2020 · similarity 0.90)
- A Temporal-Difference Approach to Policy Gradient Estimation (ICML 2022 · similarity 0.90)
- Action-Level Behavior Policy Optimization for Variance-Reduced Policy Gradients (NeurIPS 2026 · similarity 0.89)
- Learning Optimal Deterministic Policies with Stochastic Policy Gradients (ICML 2024 · similarity 0.88)
- Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity (ICML 2025 · similarity 0.88)
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.