Wasserstein Distributionally Robust Regret-Optimal Control in the Infinite-Horizon

no code implementations • 28 Dec 2023 • Taylan Kargin, Joudi Hajar, Vikrant Malik, Babak Hassibi

Our objective is to identify a control policy that minimizes the worst-case expected regret over an infinite horizon, considering all potential disturbance distributions within the ambiguity set.

Stochastic Mirror Descent in Average Ensemble Models

no code implementations • 27 Oct 2022 • Taylan Kargin, Fariborz Salehi, Babak Hassibi

The stochastic mirror descent (SMD) algorithm is a general class of training algorithms, which includes the celebrated stochastic gradient descent (SGD), as a special case.

Binary Classification

Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Regret in Linear Quadratic Control

no code implementations • 17 Jun 2022 • Taylan Kargin, Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi

By carefully prescribing an early exploration strategy and a policy update rule, we show that TS achieves order-optimal regret in adaptive control of multidimensional stabilizable LQRs.

Decision Making Decision Making Under Uncertainty +1