Abstract
We consider the problem of controlling an unknown linear dynamical system in the presence of (nonstochastic) adversarial perturbations and adversarial convex loss functions. In contrast to classical control, the a priori determination of an optimal controller here is hindered by the latter’s dependence on the yet unknown perturbations and costs. Instead, we measure regret against an optimal linear policy in hindsight, and give the first efficient algorithm that guarantees a sublinear regret bound, scaling as O(T2/3), in this setting.
Original language | English (US) |
---|---|
Pages (from-to) | 408-421 |
Number of pages | 14 |
Journal | Proceedings of Machine Learning Research |
Volume | 117 |
State | Published - 2020 |
Event | 31st International Conference on Algorithmic Learning Theory, ALT 2020 - San Diego, United States Duration: Feb 8 2020 → Feb 11 2020 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability
Keywords
- Control Theory
- Online Learning
- Robust Control
- System Identification