Research map / Bandits and online learning / Online convex optimization and games
Online linear-quadratic control regret
Learn linear-quadratic regulators online with regret guarantees.
36 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Online convex optimization and games, keyword cluster “price · pricing · auctions”
State History Tried Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
6 papers in 2023–24 and 10 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 2.6% to 3.6%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · Near-Optimal Design of Experiments via Regret Minimization (ICML 2017 · 36 citations)
- 2018 · Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator (NeurIPS 2018 · 19 citations)
- 2019 · Online Control with Adversarial Disturbances (ICML 2019 · 54 citations)
- 2020 · Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems (NeurIPS 2020 · 48 citations)
- 2021 · Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems (NeurIPS 2021 · 10 citations)
- 2022 · Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity (NeurIPS 2022 · 2 citations)
- 2023 · On the Minimax Regret for Online Learning with Feedback Graphs (NeurIPS 2023 · 0 citations)
- 2024 · Infinite-Horizon Distributionally Robust Regret-Optimal Control (ICML 2024 · 0 citations)
- 2025 · Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound (NeurIPS 2025 · 1 citation)
- 2026 · Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets (ICML 2026 · 0 citations)
Earliest papers here
- Near-Optimal Design of Experiments via Regret Minimization (ICML 2017 · 36 citations)
- Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator (NeurIPS 2018 · 19 citations)
- Online Linear Quadratic Control (ICML 2018 · 18 citations)
What has been tried
26 papers here report 125 measured changes (a component added, removed or swapped, compared with a baseline): helped 65%, no clear effect 10%, hurt 19%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use a degree 1 rational approximation instead of the non-rational DR-RO controller | AC15, r=0.01, 1, 1.5, 2, 3 · worst-case expected regret | 59.16 -> 60.49; 302.08 -> 33394.74; 488.57 -> 4475.70; 718.20 -> 9351.89; 1307.12 -> 2376.77 | Hurt | Infinite-Horizon Distributionally Robust Regret-Optimal Control (ICML 2024 · 0 citations) |
| Use fixed interpolation with C ≠ C_L instead of the adaptive LAI coefficient sequence | Stochastic SOQO, martingale minimizers · regret vs. LAI | Ω(T) | Hurt | Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization (ICML 2024 · 0 citations) |
| Increase the prediction horizon from too-small values | Circular target with zero dynamics path length · tracking performance | Helped | Predictive Linear Online Tracking for Unknown Targets (ICML 2024 · 0 citations) | |
| Increase frame stack number from 1 to 3 | Hopper domain randomization · performance | Helped | Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 16 papers; from OpenAlex and the papers' affiliations).
- California Institute of Technology · 2 papers
- Tsinghua University · 2 papers
- The University of Tokyo · 2 papers
Use it
Download BibTeX of 34 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Online learning with feedback graphs (155 papers)
- Best-of-both-worlds bandit algorithms (125 papers)
- Learning for pricing and auctions (101 papers)
- Online allocation with constraints (77 papers)
- Online decision-making with feedback structure (81 papers)
- Learning-augmented online algorithms (73 papers)
Elsewhere in the topic
- Constrained and unconstrained OCO algorithms (85 papers)
- Last-iterate convergence in games (65 papers)
- Dynamic and adaptive regret (57 papers)
- Parameter-free non-stationary online learning (45 papers)
- Fast no-regret dynamics in games (37 papers)
- Counterfactual regret minimization (15 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).