@inproceedings{1d874c756ac84e4db77f7e76b87631bf,
title = "Optimal Rates for Bandit Nonstochastic Control",
abstract = "Linear Quadratic Regulator (LQR) and Linear Quadratic Gaussian (LQG) control are foundational and extensively researched problems in optimal control. We investigate LQR and LQG problems with semi-adversarial perturbations and time-varying adversarial bandit loss functions. The best-known sublinear regret algorithm of Gradu et al. [2020] has a T 3 4 time horizon dependence, and the authors posed an open question about whether a tight rate of pT could be achieved. We answer in the affirmative, giving an algorithm for bandit LQR and LQG which attains optimal regret (up to logarithmic factors) for both known and unknown systems. A central component of our method is a new scheme for bandit convex optimization with memory, which is of independent interest.",
author = "Sun, \{Y. Jennifer\} and Stephen Newman and Elad Hazan",
note = "Publisher Copyright: {\textcopyright} 2023 Neural information processing systems foundation. All rights reserved.; 37th Conference on Neural Information Processing Systems, NeurIPS 2023 ; Conference date: 10-12-2023 Through 16-12-2023",
year = "2023",
language = "English (US)",
series = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
editor = "A. Oh and T. Neumann and A. Globerson and K. Saenko and M. Hardt and S. Levine",
booktitle = "Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023",
}