We consider the problem of controlling an unknown linear time-invariant dynamical system from a single chain of black-box interactions, and with no access to resets or offline simulation. Under the assumption that the system is controllable, we give the first efficient algorithm that is capable of attaining sublinear regret in a single trajectory under the setting of online nonstochastic control. We give finite-time regret bound of our algorithm, as well as a nearly-matching lower bound that shows this regret to be almost best-attainable by any algorithm.
View on arXiv