Antoine Moulin

Hi! I am a second-year PhD student in reinforcement learning and as part of the ELLIS PhD program, I am co-supervised by Gergely Neu and Arthur Gretton. My aim is to gain a deeper understanding of the challenges posed by large-scale reinforcement learning by identifying and exploiting structural properties of Markov decision processes (MDPs) that make large-scale learning statistically and computationally feasible.

At the moment, I am particularly interested in efficiently solving the exploration-exploitation tradeoff in infinite-horizon MDPs under (linear) function approximation. My research interests also include: online learning, offline reinforcement learning, representation learning, and more broadly learning theory.

You can reach out to me at: firstname [dot] lastname [at] upf [dot] edu.

CV  /  Twitter  /  Github

profile photo
News
  • 08/2023 - I'm going to the ELLIS symposium later this month. See you in Helsinki!
  • 07/2023 - I'll present our ICML paper at EWRL16, in Brussels.
  • 04/2023 - Our paper "Optimistic Planning by Regularized Dynamic Programming" has been accepted at ICML 2023. See you in Hawaii!
  • 04/2023 - I am attending AISTATS 2023 in Valencia, Spain.
  • 10/2022 - We are organizing RLSS 2023, that will take place in June 2023.
  • 09/2022 - I will stay in London for a week to visit the Gatsby unit at UCL.
  • 09/2022 - I will be in Milan, Italy to attend EWRL 2022.
  • 07/2022 - I am staying in Amsterdam, Netherlands for a week to attend a reinforcement learning summer school (RLSS 2022)!
  • 03/2022 - I am in Paris to attend ALT 2022.
  • 12/2021 - I am now officially a PhD student at University Pompeu Fabra.
  • show more
Publications

2023

Optimistic Planning by Regularized Dynamic Programming
Antoine Moulin, Gergely Neu
International Conference on Machine Learning (ICML), 2023
pdf

Talks

Optimistic Planning by Regularized Dynamic Programming
07/2023 - Stanford University. Stanford, CA.
08/2023 - Princeton University. Princeton, NJ.

Infinite Horizon MDPs under Function Approximation
03/2023 - Universitat Pompeu Fabra. Barcelona, Spain.

Primal-Dual Methods for Reinforcement Learning
09/2022 - Gatsby Unit, UCL. London, UK.

Introduction to JAX
09/2021 - ELLIS Doctoral Symposium 2021. Tübingen, Germany.

Virtual Sculpture
06/2018 - Journée de l'innovation (finalist). Paris, France.



Thanks Jon Barron for this nice template.