Abstract
We study linear control problems with quadratic losses and adversarially chosen tracking targets. We present an efficient algorithm for this problem and show that, under standard conditions on the linear system, its regret with respect to an op timal linear policy grows as where T is the number of rounds of the game. We also study a problem with adversarially chosen transition dynamics; we present an exponentiallyweighted average algorithm for this problem, an we give regret bounds that grow as