Research map / Learning theory and algorithms / Sample complexity
Distributionally Robust 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 Frank-Wolfe with Kalman filtering and dynamic programming instead of direct SDP solving | Distributionally robust LQG · Synthetic LQG problems across planning horizons | runtime | Helped |
| Use Frank-Wolfe with parallel covariance subproblems | Distributionally robust LQG · Synthetic problem instances with T=10 | iterations to highly accurate solution: 50 iterations | Helped |
| Allow Wasserstein ambiguity around nominal Gaussian noise distributions | LQG control · Finite-horizon distributionally robust LQG | optimal policy structure | No clear effect |
| Optimize over the Wasserstein ambiguity set rather than assuming a known noise distribution | Distributionally robust LQG · Finite-horizon distributionally robust LQG | worst-case noise distribution | No clear effect |
Closest papers by meaning
- Wasserstein Distributionally Robust Kalman Filtering (NeurIPS 2018 · similarity 0.88)
- Infinite-Horizon Distributionally Robust Regret-Optimal Control (ICML 2024 · similarity 0.88)
- Certainty Equivalence is Efficient for Linear Quadratic Control (NeurIPS 2019 · similarity 0.88)
- Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator (NeurIPS 2018 · similarity 0.86)
- Safe-PG-LQR: Provably Safe, Convergent and Optimal Model-Free Linear Quadratic Regulator with Hard Constraints (NeurIPS 2026 · similarity 0.85)
- Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator (ICLR 2025 · similarity 0.83)
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.