Nov 18, 2020 · This paper presents local asymptotic minimax regret lower bounds for adaptive Linear Quadratic Regulators (LQR). We consider affinely parametrized B-matrices ...

We explicitly characterize the notion of an uninformative optimal policy in terms of the nullspaces of system-theoretic quantities and the particular instance ...

Local asymptotic minimax regret lower bounds for adaptive Linear Quadratic Regulators are presented and it is shown that if the parametrization induces an ...

Nov 18, 2020 · This paper presents local asymptotic minimax regret lower bounds for adaptive Linear Quadratic Regulators (LQR).

Apr 30, 2021 · Since the optimal linear feedback law is 0 if and only if θ = 0, it follows that scalar LQR is uninformative if and only if the input matrix is ...

2022. On uninformative optimal policies in adaptive lqr with unknown b-matrix. I Ziemann, H Sandberg. Learning for Dynamics and Control, 213-226, 2021. 10, 2021.

After defining the intrinsic notion of an uninformative optimal policy in terms of a singularity condition for Fisher information we obtain local minimax regret ...

On Uninformative Optimal Policies in Adaptive LQR with Unknown B-Matrix. In: Proceedings of the 3rd Conference on Learning for Dynamics and Control, L4DC ...

On Uninformative Optimal Policies in Adaptive LQR with Unknown B-Matrix · no code implementations • 18 Nov 2020 • Ingvar Ziemann, Henrik Sandberg.

On Uninformative Optimal Policies in Adaptive LQR with Unknown B-Matrix. Ingvar Ziemann, Henrik Sandberg; Proceedings of the 3rd Conference on Learning for ...