Research map / Learning theory and algorithms / Sample complexity
Global Convergence of Two-Timescale Actor-Critic for Solving 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 single-sample two-timescale natural AC rather than the cited single-sample two-timescale AC baseline | Two-timescale AC for LQR · LQR | optimality | Helped |
| Use single-sample rather than multi-sample two-timescale AC | Two-timescale AC for LQR · LQR | sample complexity: \mathcal{O}(\epsilon^{-4}) -> \mathcal{O}(\epsilon^{-2.5}) | Helped |
| Use single-sample two-timescale AC rather than double-loop AC | Actor-critic for LQR · LQR | sample complexity: \mathcal{O}(\epsilon^{-5}) -> \mathcal{O}(\epsilon^{-2.5}) | Helped |
| Use the proposed single-sample two-timescale AC instead of the compared double-loop AC and zeroth-order method | LQR algorithms · Two simulated LQR examples | sample efficiency | Helped |
Closest papers by meaning
- Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation (ICML 2024 · similarity 0.91)
- On the Convergence of Single-Timescale Actor-Critic (NeurIPS 2025 · similarity 0.91)
- On the Convergence of Continuous Single-timescale Actor-critic (ICML 2025 · similarity 0.90)
- Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation (AAAI 2025 · similarity 0.90)
- Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization (ICML 2024 · similarity 0.89)
- Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning (ICML 2024 · 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.