Research map / Bandits and online learning / Online convex optimization and games
Non-Stochastic Control with Bandit Feedback
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 |
|---|---|---|---|
| introduce intentional delay in gradient updates | BCO with Memory · Bandit convex optimization with memory | regret: \mathcal{O}\left(T^{3/4} H^{3/2} d D^{4/3} G^{2/3} \right) | Helped |
| apply BCO with Memory to train a disturbance action controller | Bandit Perturbation Controller · Non-stochastic control, known LDS | regret: \mathcal{O}\left(T^{3/4}\log^{5/2}T\right) | Helped |
| add an exploration phase to estimate unknown dynamics before running BPC | BPC with system identification · Non-stochastic control, unknown LDS | regret: \mathcal{O}\left(T^{3/4}\log^{5/2}T\right) | Helped |
| use perturbation controllers instead of the LQR baseline | BPC and GPC · Sinusoidal noise, known dynamics | cost | Helped |
| use perturbation controllers instead of the LQR baseline | BPC and GPC · i.i.d. Gaussian noise, known dynamics | cost | No clear effect |
Closest papers by meaning
- Tight Rates for Bandit Control Beyond Quadratics (NeurIPS 2024 · similarity 0.94)
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024 · similarity 0.90)
- Handling Heterogeneous Curvatures in Bandit LQR Control (ICML 2024 · similarity 0.89)
- Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback (NeurIPS 2024 · similarity 0.89)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · similarity 0.88)
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · 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.