activity
20202025
collaborators

6 papers

stat.ML2025

Refined PAC-Bayes Bounds for Offline Bandits

Amaury Gouverneur, Tobias J. Oechtering, Mikael Skoglund

In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et…

stat.ML2025

An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces

Amaury Gouverneur, Borja Rodriguez Gálvez, Tobias Oechtering +1

This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015…

stat.ML2024

An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits

Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering +1

We study the performance of the Thompson Sampling algorithm for logistic bandit problems. In this setting, an agent receives binary rewards with probabilities determined by a logis…

cs.LG2024

Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality

Raghav Bongole, Amaury Gouverneur, Borja Rodríguez-Gálvez +2

We study agents acting in an unknown environment where the agent's goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for…

stat.ML2024

Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems

Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering +1

This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems. It builds upon the information-theoretic framework of [Russo and Van Roy…

eess.SY2020

Optimal measurement budget allocation for particle filtering

Antoine Aspeel, Amaury Gouverneur, Raphaël M. Jungers +1

Particle filtering is a powerful tool for target tracking. When the budget for observations is restricted, it is necessary to reduce the measurements to a limited amount of samples…