Optimal Rates for Bandit Nonstochastic Control

Y. Jennifer Sun, Stephen Newman, Elad Hazan

Research output: Contribution to journalConference articlepeer-review


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.

Original languageEnglish (US)
JournalAdvances in Neural Information Processing Systems
StatePublished - 2023
Event37th Conference on Neural Information Processing Systems, NeurIPS 2023 - New Orleans, United States
Duration: Dec 10 2023Dec 16 2023

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing


Dive into the research topics of 'Optimal Rates for Bandit Nonstochastic Control'. Together they form a unique fingerprint.

Cite this