Research map / Learning theory and algorithms / Prediction and decision losses
Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs
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 robust planning over confidence region instead of nominal (estimated-dynamics) planning | Robust MPC · Obstacle avoidance | failure rate (%): 4 -> 0 | Helped |
| use robust planning instead of nominal planning | Robust MPC · Obstacle avoidance | minimum return: 2.8 -> 10.4 | Helped |
| use robust planning instead of nominal planning | Robust MPC · Obstacle avoidance | average return: 13.8 -> 13.0 | Hurt |
| use robust multi-model planning instead of Nominal 2 (picks model with min prediction error) | Robust MPC · Intersection driving | failure rate (%): 33 -> 0 | Helped |
| use robust multi-model planning instead of Nominal 1 (knows true routes) | Robust MPC · Intersection driving | average return: 7.3 -> 7.1 | Hurt |
| use model-based robust planning instead of model-free DQN trained 3000 episodes | Robust MPC · Obstacle avoidance | failure rate (%): 6 -> 0 | Helped |
| use robust planning instead of DQN | Robust MPC · Intersection driving | average return: 6.3 -> 7.1 | Helped |
Closest papers by meaning
- Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator (ICLR 2025 · similarity 0.85)
- Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control (ICLR 2024 · similarity 0.85)
- Infinite-Horizon Distributionally Robust Regret-Optimal Control (ICML 2024 · similarity 0.85)
- Differentiable Nonlinear Model Predictive Control (NeurIPS 2026 · similarity 0.85)
- Parameter-Efficient Fine-Tuning with Controls (ICML 2024 · similarity 0.84)
- Disentangling Linear Quadratic Control with Untrusted ML Predictions (NeurIPS 2024 · similarity 0.84)
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.