Eloïse Berthier — accepted AI-conference papers

2026

Benchmarking XAI Explanations with Human-Aligned Evaluations

Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier, Anna Hedström, Patricia Delhomme, David Filliat +6

AAAI 2026technical

We introduce PASTA (Perceptual Assessment System for explanaTion of Artificial Intelligence), a novel human-centric framework for evaluating eXplainable AI (XAI) techniques in computer vision. Our first contribution is the creation of the PASTA-dataset, the first large-scale benchmark that spans a d

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

On Double Descent in Reinforcement Learning with LSTD and Random Features

David Brellmann, Eloïse Berthier, David Filliat, Goran Frehse

ICLR 2024poster

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL). Their performance is heavily influenced by the size of the neural network. While in supervised learning, the regime of over-parameterization and its benefits are well understood, the situation in RL is much less…

Cited by 1 Source ↗PDF ↗Scholar ↗

2022

A Non-asymptotic Analysis of Non-parametric Temporal-Difference Learning

Eloïse Berthier, Ziad Kobeissi, Francis Bach

NeurIPS 2022accept

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 independent and Markovian observation settings. In particular, when TD is performed in a universal reproducing kernel Hilb…

Cited by 3 Source ↗PDF ↗Scholar ↗