Abstract
We study the control of linear dynamical systems with adversarial disturbances, as opposed to statistical noise. We present an efficient algorithm that achieves nearly-tight regret bounds in this setting. Our result generalizes upon previous work in two main aspects: the algorithm can accommodate adversarial noise in the dynamics, and can handle general convex costs.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 111-119 |
| Number of pages | 9 |
| Journal | Proceedings of Machine Learning Research |
| Volume | 97 |
| State | Published - 2019 |
| Externally published | Yes |
| Event | 36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States Duration: Jun 9 2019 → Jun 15 2019 |
All Science Journal Classification (ASJC) codes
- Software
- Control and Systems Engineering
- Statistics and Probability
- Artificial Intelligence
Fingerprint
Dive into the research topics of 'Online Control with Adversarial Disturbances'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver