Research map / Bandits and online learning / Online convex optimization and games
Learning Linear-Quadratic Regulators Efficiently with only $\sqrtT$ Regret
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 optimistic policies computed from a sequence of relaxed semidefinite programs | Learning unknown-dynamics LQR · Unknown-dynamics LQR, T rounds | regret: O(T^{2/3}) -> \widetilde{O}(\sqrt{T}) | Helped |
| Warm up using a known strongly stable policy with Gaussian action exploration before running OSLO | OSLO · Unknown-dynamics LQR, T rounds | regret: O \biggl( \frac{\alpha_1 n^2 \nu^{5} \vartheta \kappa_{0}^4}{\alpha_0^{5} \sigma^{8} \gamma_{0}^2} (n + k \vartheta^2 \k | Helped |
Closest papers by meaning
- Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently (ICML 2020 · similarity 0.95)
- Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret (ICML 2021 · similarity 0.94)
- Online Linear Quadratic Control (ICML 2018 · similarity 0.91)
- Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation (ICML 2020 · similarity 0.91)
- Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator (ICLR 2025 · similarity 0.90)
- Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator (NeurIPS 2018 · similarity 0.90)
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.