Research map / Bandits and online learning / Online convex optimization and games
Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis
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 |
|---|---|---|---|
| increase prediction window W (more gradient iterations K) | RHGC (RHGD, RHTM, RHAG) · LQ tracking (n=2, m=1, p=2) | log regret | Helped |
| use accelerated gradient (triple momentum or Nesterov) instead of vanilla gradient descent (ablation) | RHGC · LQ tracking | regret | Helped |
| RHGC instead of suboptimal fast-gradient MPC with 1 iteration | online control with predictions · LQ tracking | regret | Helped |
| increase iterations of suboptimal MPC (1 to 3 to 5) | subMPC · LQ tracking | regret | Mixed |
| longer lookahead window (W=40 to W=80) | RHGC · two-wheel robot path tracking (nonlinear) | tracking performance (qualitative) | Helped |
Closest papers by meaning
- Rate-Optimal Online Convex Optimization in Adaptive Linear Control (NeurIPS 2022 · similarity 0.92)
- Logarithmic Regret for Online Control (NeurIPS 2019 · similarity 0.91)
- Online Control of Unknown Time-Varying Dynamical Systems (NeurIPS 2021 · similarity 0.91)
- Online Linear Quadratic Control (ICML 2018 · similarity 0.90)
- Geometric Exploration for Online Control (NeurIPS 2020 · similarity 0.89)
- Predictive Linear Online Tracking for Unknown Targets (ICML 2024 · similarity 0.89)
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.