Research map / Bandits and online learning / Online convex optimization and games
Online Linear Quadratic Control
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 SDP-based Online Gradient Descent over steady-state covariance distributions | Online LQ control · Adversarial quadratic costs | regret: O\lr{ \frac{\kappa^{10} \lambda^{5}}{\gamma^{2.5}\sigma^{3}} C \sqrt{T} } | Helped |
| Use Follow the Lazy Leader with an SDP-based oracle and resets | Online LQ control · Adversarial quadratic costs | regret: O \Lr{ (d+k)^{3/4} \sqrt{C \nu(C_r + C \nu) T} } | Helped |
| Use FLL rather than the Recent strategy | Data center cooling control · Uniform random power costs | normalized regret | Helped |
| Use FLL rather than the Recent strategy | Data center cooling control · Slowly varying power costs | normalized regret | Hurt |
Closest papers by meaning
- Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt$T Regret (ICML 2021 · similarity 0.93)
- Rate-Optimal Online Convex Optimization in Adaptive Linear Control (NeurIPS 2022 · similarity 0.91)
- A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems (NeurIPS 2026 · similarity 0.89)
- Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator (ICLR 2025 · similarity 0.89)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.89)
- Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization (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.