6 papers
A Stochastic Optimization Approach to Control-Affine Optimal Control Problems
Eloïse Berthier, Ziad Kobeissi, Francis Bach
We consider control-affine optimal control problems on the torus, where the dynamics and cost functions are only accessed through samples. Starting from a weak formulation of such…
Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples
Ziad Kobeissi, Éloïse Berthier
In this paper, we study the finite-time behavior of the TD(0) temporal-difference method with linear function approximation (LFA). We consider on-policy independent and identically…
Sampling-Based Global Optimal Control and Estimation via Semidefinite Programming
Antoine Groudiev, Fabian Schramm, Éloïse Berthier +2
Global optimization has gained attraction over the past decades, thanks to the development of both theoretical foundations and efficient numerical routines. Among recent advances,…
A Non-asymptotic Analysis of Non-parametric Temporal-Difference Learning
Eloïse Berthier, Ziad Kobeissi, Francis Bach
Temporal-difference learning is a popular algorithm for policy evaluation. In this paper, we study the convergence of the regularized non-parametric TD(0) algorithm, in both the in…
Infinite-Dimensional Sums-of-Squares for Optimal Control
Eloïse Berthier, Justin Carpentier, Alessandro Rudi +1
We introduce an approximation method to solve an optimal control problem via the Lagrange dual of its weak formulation. It is based on a sum-of-squares representation of the Hamilt…
Amplifying Rényi Differential Privacy via Shuffling
Eloïse Berthier, Sai Praneeth Karimireddy
Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the Rényi differential privacy of…