Timezone: »

 
Poster
Non-Stochastic Control with Bandit Feedback
Paula Gradu · John Hallman · Elad Hazan

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1289

We study the problem of controlling a linear dynamical system with adversarial perturbations where the only feedback available to the controller is the scalar loss, and the loss function itself is unknown. For this problem, with either a known or unknown system, we give an efficient sublinear regret algorithm. The main algorithmic difficulty is the dependence of the loss on past controls. To overcome this issue, we propose an efficient algorithm for the general setting of bandit convex optimization for loss functions with memory, which may be of independent interest.

Author Information

Paula Gradu (Princeton University, Google AI Princeton)
John Olof Hallman (Princeton University)
Elad Hazan (Princeton University)

More from the Same Authors