Search Results for author: Alexis Jacq

Found 4 papers, 1 papers with code

C3PO: Learning to Achieve Arbitrary Goals via Massively Entropic Pretraining

no code implementations7 Nov 2022 Alexis Jacq, Manu Orsini, Gabriel Dulac-Arnold, Olivier Pietquin, Matthieu Geist, Olivier Bachem

Given a particular embodiment, we propose a novel method (C3PO) that learns policies able to achieve any arbitrary position and pose.

Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act

no code implementations16 Mar 2022 Alexis Jacq, Johan Ferret, Olivier Pietquin, Matthieu Geist

We deem those states and corresponding actions important since they explain the difference in performance between the default and the new, lazy policy.

Atari Games Decision Making +1

Foolproof Cooperative Learning

no code implementations24 Jun 2019 Alexis Jacq, Julien Perolat, Matthieu Geist, Olivier Pietquin

We prove that in repeated symmetric games, this algorithm is a learning equilibrium.

Cannot find the paper you are looking for? You can Submit a new open access paper.