Research map / Bandits and online learning / Online convex optimization and games
Logarithmic Regret for Adversarial Online 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 approximate advantages with finite lookahead and exp-concave online learning rather than stationary-cost methods | Online linear-quadratic control with known dynamics and quadratic costs · Adversarial disturbances | regret: \sqrt{T} to \cO_{\star}(d_{\mathbf{x}}d_{\mathbf{u}}\log^{3}T) | Helped |
| Use VAW instead of ONS as the base learner | Riccatitron · Online linear-quadratic control with adversarial disturbances | regret: \cO_{\star}(d_{\mathbf{x}}d_{\mathbf{u}}\sqrt{d_{\mathbf{x}}\wedged_{\mathbf{u}}}\log^{3}T) to \cO_{\star}(d_{\mathbf{x} | Helped |
Closest papers by meaning
- Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions (AAAI 2025 · similarity 0.88)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.88)
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024 · similarity 0.87)
- Tight Rates for Bandit Control Beyond Quadratics (NeurIPS 2024 · similarity 0.87)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.87)
- Near-Optimal Regret in Adversarial Kernel Bandits (NeurIPS 2026 · 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.