This page contains:
News
2022
- Dec 14th, 2022: Léonard Hussenot defends his PhD.
- Dec 9th, 2022: Romain Gautron defends his PhD.
- Dec 8th, 2022: Sarah Perrin defends her PhD.
- Dec 6th, 2022: Dorian Baudry defends his PhD.
- Nov. 2022: Scool presents 6 papers at NeurIPS.
- Sep 9th, 2022: Clémence Reda defends her PhD.
- July 6th, 2022: Jean Tarbouriech defends his PhD.
- July 4th, 2022: Johan Ferret defends his PhD.
- We co-organize the “complex feedback in online learning” workshop at ICML, to be held in July.
- May 25th, 2022: Pierre Schegg defends his PhD.
- Mar 18th, 2022: Omar Darwiche Domingues defends his PhD.
- Mar 17th, 2022: Members of Scool and Magnet teams are organizing “Fairness in Machine Learning Day” on 17th or March, 2022 at Amphi B of Inria Lille. Check this link for details.
- Feb 2022: Scool presents 4 papers at AAAI 2022
2021
- Oct. 2021: About the RAID project: read on the Inria website
- Scool presents 9 papers at NeurIPS 2021: see you there
- 3 PhD defenses Fall 2021:
- Yannis Flet-Berliac, 6 October 2021, the dissertation.
- Xuedong Shang, 29 September 2021, the dissertation
- Mathieu Seurin, 28 September 2021, the dissertation.
- May 2021: we present 4 papers at ICLR, and some more papers at satellite workshops.
- April 2021: we present 3 papers at AI & Stats.
- March 2021: Édouard Leurent, last SequeL PhD student, is awarded with the best PhD thesis price of the GdR MACS and by the “Section Automatique du Club EEA”, on CNRS website.
- February 2021: Scool presents a paper in AAAI 2021 aiming to verify different fairness metrics of machine learning algorithms.
- January 2021: first release of the RL-berry: A Reinforcement Learning Library for Research and Education, an easy to use RL software library with the implementation of state-of-the-art algorithms.
2020
- Philippe Preux and Odalric-Ambrym Maillard are granted an “AI chair” named Apprenf funded by I-Site ULNE, Métropole Européenne de Lille (MEL), ANR, Université de Lille, Inria. This chair will end in September 2023. The goal is to financially support their research activities in reinforcement learning.
- 15 December 2020: Julien Seznec defends his PhD.
- Join us at virtual NeurIPS: Scool presents 7 papers, one with a plenary talk.
- 30 November 2020: Pierre Perrault defends his PhD.
- 13 November 2020: Émilie Kaufmann defends her HDR.
- 1 November 2020: birth of Scool.
Seminars (more details here)
- July 8th, 2022: Taira Tsuchiya (visiting PhD student from Kyoto University) will give a talk.
- 25 February 2022: Memory Saving Strategies for Deep Neural Network Training, by Alena Shilova (Inria Scool).
- 18 February 2022: Robustness via distributional dynamic programming, by Mastane Achab (Universitat Pompeu Fabra).
- 11 February 2022: Routing in an Uncertain World: Adaptivity, Efficiency, and Equilibrium, by Dong Quan Vu (Grenoble Computer Science Laboratory – LIGLAB).
- 4 February 2022: A Unified Perspective on Value Backup and Exploration in Monte Carlo Tree Search, by Tuan Dam (TU Darmstadt).
- 28 January 2022: A/B/n Testing with Control in the Presence of Subpopulations, by Wooter M. Koolen (Centrum Wiskunde & Informatica, Amsterdam).
- 21 January 2022: From Lyapunov to model free reinforcement learning in games, by Julien Perolat (Deepmind).
- 14 January 2022: Verification and Explanation of Fairness in Machine Learning, by Bishwamittra Ghosh (National University of Singapore).
- 7 January 2022: Fixed-confidence top-m identification for structured models, by Clémence Réda (Inria Scool).
- 17 December 2021: Concentration of exponential families with several parameters, by Rémy Degenne (Inria Scool).
- 26 November 2021: From Optimality to Robustness: Dirichlet Randomized Exploration in Stochastic Bandits, by Patrick Saux (Inria Scool).
- 19 November 2021: Choosing Answers in ε-Best-Answer Identification for Linear Bandits, by Marc Jourdan (Inria Scool).
- 5 November 2021: Testing by betting, by Rianne de Heide (Inria Scool).
- 29 October 2021: Exploiting Structure in State-Action Sequences: Reversibility, Redundancy, by Nathan Grinsztajn (Inria Scool).
- 22 October 2021: Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits, by Reda Ouhamma (Inria Scool).
- 1 October 2021: rlberry: A Reinforcement Learning Library for Research and Education, Omar Darwiche Domingues (Inria Scool).
- 24 September 2021: On the efficiency of subsampling algorithms for exploration in bandit, Dorian Baudry (Inria Scool).
- 9 July 2021: M-estimation and Median of Means applied to statistical learning,
Timothée Mathieu (Université Paris-Saclay). - 25 June 2021: Problem-Dependent Regret Lower Bounds for Finite-Horizon MDPs, Andrea Tirinzoni (Inria Scool).
- 18 June 2021: New insights on concentrations inequalities for martingales,
applications to statistics and machine learning, Taieb Touati (Sorbonne Université). - 11 June 2021: Reinforcement Learning in Non-Stationary Markov Decision Processes, Erwan Lecarpentier (ISAE-SUPAERO).
- 21 May 2021: Cooperation in Online Learning, Riccardo Della Vecchia (Bocconi U. Milan).
- 23 April 2021: Q-Learning algorithms and algorithmic collusion in online markets, by Luc Rocher (Imperial College London).
- 9 April 2021: Restless stochastic bandits with correlations (arXiv), by Oleksandr Zadorozhnyi (University of Potsdam).
- 2 April 2021: Causal Populations Identification through Hidden Distributions Estimation, by Céline Béji (Paris-Dauphine).
- 29 January 2021: Predicting the clinical worsening of Covidom patients from their symptoms, by Jill-Jênn Vie, Vianney Taquet and Clémence Léguillette (Inria Scool).
- 15 January 2021: Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling, by Nathan Grinsztajn (Inria Scool).
- 4 January 2021: Solving stochastic bandits with an adversarial game, by Rémy Degenne (Inria Scool).
- 27 November 2020: What is a Mean Field Game? Why is it interesting for Multi-agent RL? Why RL can also help to solve Mean Field Games?, by Sarah Perrin (Inria Scool).
- 20 November 2020: High-Probability Regret Bounds for Online Linear Regression, by Reda Ouhamma (Inria Scool).
