Research map / Reinforcement learning / Policy gradient and actor-critic
Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
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 |
|---|---|---|---|
| Use Gauss-Newton updates instead of natural policy gradient updates | Exact policy optimization for LQR · Infinite-horizon LQR | convergence rate | Helped |
| Use natural policy gradient updates instead of ordinary gradient descent | Policy optimization for LQR · Infinite-horizon LQR | convergence rate | Helped |
| Estimate gradient and covariance from simulated trajectories rather than using exact model-based quantities | Natural policy gradient · Infinite-horizon LQR, model-free | cost suboptimality | Helped |
| Estimate the gradient from simulated trajectories rather than using exact gradients | Gradient descent · Infinite-horizon LQR, model-free | cost suboptimality | Helped |
| Use a full-rank distribution of initial states | Policy gradient methods for LQR · Infinite-horizon LQR | global optimality of stationary points | Helped |
Closest papers by meaning
- Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings (AAAI 2022 · similarity 0.89)
- Identifying Policy Gradient Subspaces (ICLR 2024 · similarity 0.89)
- Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States (ICML 2024 · similarity 0.88)
- Learning Optimal Deterministic Policies with Stochastic Policy Gradients (ICML 2024 · similarity 0.88)
- Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity (ICML 2025 · similarity 0.87)
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.