Timezone: »

Bandit Linear Control
Asaf Benjamin Cassel · Tomer Koren

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1459

We consider the problem of controlling a known linear dynamical system under stochastic noise, adversarially chosen costs, and bandit feedback. Unlike the full feedback setting where the entire cost function is revealed after each decision, here only the cost incurred by the learner is observed. We present a new and efficient algorithm that, for strongly convex and smooth costs, obtains regret that grows with the square root of the time horizon T. We also give extensions of this result to general convex, possibly non-smooth costs, and to non-stochastic system noise. A key component of our algorithm is a new technique for addressing bandit optimization of loss functions with memory.

Author Information

Asaf Benjamin Cassel (Tel Aviv University)
Tomer Koren (Tel Aviv University & Google)

Related Events (a corresponding poster, oral, or spotlight)

  • 2020 Spotlight: Bandit Linear Control »
    Thu. Dec 10th 03:00 -- 03:10 PM Room Orals & Spotlights: Reinforcement Learning

More from the Same Authors