Towards Minimax Optimality of Model-based Robust Reinforcement Learning

no code implementations • 10 Feb 2023 • Pierre Clavier, Erwan Le Pennec, Matthieu Geist

In this paper, we consider uncertainty sets defined with an $L_p$-ball (recovering the TV case), and study the sample complexity of \emph{any} planning algorithm (with high accuracy guarantee on the solution) applied to an empirical RMDP estimated using the generative model.

reinforcement-learning Reinforcement Learning (RL)

Robust Reinforcement Learning with Distributional Risk-averse formulation

no code implementations • 14 Jun 2022 • Pierre Clavier, Stéphanie Allassonière, Erwan Le Pennec

Robust Reinforcement Learning tries to make predictions more robust to changes in the dynamics or rewards of the system.

Distributional Reinforcement Learning reinforcement-learning +1

Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning

1 code implementation • 23 Jul 2020 • Frédéric Logé, Erwan Le Pennec, Habiboulaye Amadou-Boubacar

Patients with diabetes who are self-monitoring have to decide right before each meal how much insulin they should take.

reinforcement-learning Reinforcement Learning (RL)

Learning from both experts and data

no code implementations • 20 Oct 2019 • Rémi Besson, Erwan Le Pennec, Stéphanie Allassonnière

In this context, it is common to rely first on an initial domain knowledge a priori before proceeding to an online data acquisition.

A Model-Based Reinforcement Learning Approach for a Rare Disease Diagnostic Task

no code implementations • 25 Nov 2018 • Rémi Besson, Erwan Le Pennec, Stéphanie Allassonnière, Julien Stirnemann, Emmanuel Spaggiari, Antoine Neuraz

In this work, we present our various contributions to the objective of building a decision support tool for the diagnosis of rare diseases.

Model-based Reinforcement Learning reinforcement-learning +1