Research map / Bandits and online learning / Online convex optimization and games
Optimal Rates for Bandit Nonstochastic 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 EBPC instead of BPC | Bandit control with semi-adversarial perturbations · Bandit LQG, known system | regret: \tilde{O}(T^{\frac{3}{4}}) -> \tilde{O}(\sqrt{T}) | Helped |
| Apply EBPC after estimating the Markov operator with SysEst-LS | Bandit LQG with unknown system dynamics · Bandit LQG, unknown system | regret | Helped |
| Use ellipsoidal gradient estimation for quadratic losses with memory | Bandit convex optimization with memory · Quadratic strongly convex losses | regret: \tilde{\mathcal{O}}\left(\frac{\beta n}{\sigma}\sqrt{T}\right) | Helped |
| Use EBPC rather than BPC | Control of a barely-stable damped double-integrator · Sinusoidal and Gaussian-walk perturbations | loss | Helped |
| Use EBPC rather than BPC | Control of a barely-stable damped double-integrator · Gaussian perturbations | loss | No clear effect |
Closest papers by meaning
- Tight Rates for Bandit Control Beyond Quadratics (NeurIPS 2024 · similarity 0.94)
- Handling Heterogeneous Curvatures in Bandit LQR Control (ICML 2024 · similarity 0.92)
- Non-Stochastic Control with Bandit Feedback (NeurIPS 2020 · similarity 0.92)
- Bandit Linear Control (NeurIPS 2020 · similarity 0.91)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · similarity 0.88)
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024 · similarity 0.88)
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.