no code implementations • 10 Nov 2023 • Joudi Hajar, Oron Sabag, Babak Hassibi
This paper studies online solutions for regret-optimal control in partially observable systems over an infinite-horizon.
no code implementations • 3 Jun 2022 • Oron Sabag, Sahin Lale, Babak Hassibi
The key techniques that underpin our explicit solution is a reduction of the control problem to a Nehari problem, along with a novel factorization of the clairvoyant controller's cost.
no code implementations • 4 May 2021 • Oron Sabag, Gautam Goel, Sahin Lale, Babak Hassibi
Motivated by competitive analysis in online learning, as a criterion for controller design we introduce the dynamic regret, defined as the difference between the LQR cost of a causal controller (that has only access to past disturbances) and the LQR cost of the \emph{unique} clairvoyant one (that has also access to future disturbances) that is known to dominate all other controllers.
1 code implementation • 25 Jan 2021 • Oron Sabag, Babak Hassibi
For the important case of signals that can be described with a time-invariant state-space, we provide an explicit construction for the regret optimal filter in the estimation (causal) and the prediction (strictly-causal) regimes.
1 code implementation • 27 Jan 2020 • Ziv Aharoni, Oron Sabag, Haim Henry Permuter
In this paper, we propose a novel method to compute the feedback capacity of channels with memory using reinforcement learning (RL).