title | abstract | layout | series | publisher | issn | id | month | tex_title | firstpage | lastpage | page | order | cycles | bibtex_author | author | date | address | container-title | volume | genre | issued | extras | ||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Black-Box Control for Linear Dynamical Systems |
We consider the problem of black-box control: the task of controlling an unknown linear time-invariant dynamical system from a single trajectory without a stabilizing controller. Under the assumption that the system is controllable, we give the first {\it efficient} algorithm that is capable of attaining sublinear regret under the setting of online nonstochastic control. This resolves an open problem since the work of Abbasi-Yadkori and Szepesvari(2011) on the stochastic LQR problem, and in a more challenging setting that allows for adversarial perturbations and adversarially chosen changing convex loss functions. We give finite-time regret bounds for our algorithm on the order of |
inproceedings |
Proceedings of Machine Learning Research |
PMLR |
2640-3498 |
chen21c |
0 |
Black-Box Control for Linear Dynamical Systems |
1114 |
1143 |
1114-1143 |
1114 |
false |
Chen, Xinyi and Hazan, Elad |
|
2021-07-21 |
Proceedings of Thirty Fourth Conference on Learning Theory |
134 |
inproceedings |
|