1 code implementation • 23 May 2024 • Hector Kohler, Quentin Delfosse, Riad Akrour, Kristian Kersting, Philippe Preux
We empirically demonstrate that INTERPRETER compact tree programs match oracles across a diverse set of sequential decision tasks and evaluate the impact of our design choices on interpretability and performances.
no code implementations • 16 Apr 2024 • Hector Kohler, Quentin Delfosse, Paul Festor, Philippe Preux
What reinforcement learning paradigms, are the most suited to develop interpretable agents?
no code implementations • 26 Feb 2024 • Pierre Erbacher, Jian-Yun Nie, Philippe Preux, Laure Soulier
Conversational systems have made significant progress in generating natural language responses.
no code implementations • 10 Nov 2023 • Pierre Erbacher, Jian-Yun Nie, Philippe Preux, Laure Soulier
The only two datasets known to us that contain both document relevance judgments and the associated clarification interactions are Qulac and ClariQ.
no code implementations • 23 Sep 2023 • Hector Kohler, Riad Akrour, Philippe Preux
We show in this paper that deep RL can fail even on simple toy tasks of this class.
no code implementations • 22 Sep 2023 • Hector Kohler, Riad Akrour, Philippe Preux
Finding an optimal decision tree for a supervised learning task is a challenging combinatorial problem to solve at scale.
no code implementations • 31 Aug 2023 • Patrick Saux, Pierre Bauvin, Violeta Raverdy, Julien Teigny, Hélène Verkindt, Tomy Soumphonphakdy, Maxence Debert, Anne Jacobs, Daan Jacobs, Valerie Monpellier, Phong Ching Lee, Chin Hong Lim, Johanna C Andersson-Assarsson, Lena Carlsson, Per-Arne Svensson, Florence Galtier, Guelareh Dezfoulian, Mihaela Moldovanu, Severine Andrieux, Julien Couster, Marie Lepage, Erminia Lembo, Ornella Verrastro, Maud Robert, Paulina Salminen, Geltrude Mingrone, Ralph Peterli, Ricardo V Cohen, Carlos Zerrweck, David Nocca, Carel W Le Roux, Robert Caiazzo, Philippe Preux, François Pattou
We aimed to develop a model using machine learning to provide individual preoperative prediction of 5-year weight loss trajectories after surgery.
no code implementations • 19 Jun 2023 • Timothée Mathieu, Riccardo Della Vecchia, Alena Shilova, Matheus Medeiros Centa, Hector Kohler, Odalric-Ambrym Maillard, Philippe Preux
When comparing several RL algorithms, a major question is how many executions must be made and how can we ensure that the results of such a comparison are theoretically sound.
no code implementations • 11 Apr 2023 • Hector Kohler, Riad Akrour, Philippe Preux
A given supervised classification task is modeled as a Markov decision problem (MDP) and then augmented with additional actions that gather information about the features, equivalent to building a DT.
no code implementations • 16 Oct 2022 • Riccardo Della Vecchia, Alena Shilova, Philippe Preux, Riad Akrour
Compared to these learning frameworks, one of the major difficulties of RL is the absence of i. i. d.
no code implementations • 20 Sep 2022 • Matheus Centa, Philippe Preux
Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents.
no code implementations • 7 Jul 2022 • Romain Gautron, Emilio J. Padrón, Philippe Preux, Julien Bigot, Odalric-Ambrym Maillard, David Emukpere
gym-DSSAT is a gym interface to the Decision Support System for Agrotechnology Transfer (DSSAT), a high fidelity crop simulator.
no code implementations • 20 Oct 2021 • Toby Johnstone, Nathan Grinsztajn, Johan Ferret, Philippe Preux
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question.
no code implementations • 29 Sep 2021 • Nathan Grinsztajn, Toby Johnstone, Johan Ferret, Philippe Preux
Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question.
no code implementations • NeurIPS 2021 • Nathan Grinsztajn, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist
We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning (RL).
no code implementations • 4 Jun 2021 • Nathan Grinsztajn, Louis Leconte, Philippe Preux, Edouard Oyallon
We present a new approach for learning unsupervised node representations in community graphs.
no code implementations • ICLR Workshop GTRL 2021 • Nathan Grinsztajn, Philippe Preux, Edouard Oyallon
In this work, we study the behavior of standard models for community detection under spectral manipulations.
1 code implementation • 20 May 2021 • Mathieu Seurin, Florian Strub, Philippe Preux, Olivier Pietquin
Sparse rewards are double-edged training signals in reinforcement learning: easy to design but hard to optimize.
no code implementations • ICLR Workshop SSL-RL 2021 • Mathieu Seurin, Florian Strub, Philippe Preux, Olivier Pietquin
We evaluate RAM on the procedurally-generated environment MiniGrid, against state-of-the-art methods.
1 code implementation • ICLR 2021 • Yannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist
Despite definite success in deep reinforcement learning problems, actor-critic algorithms are still confronted with sample inefficiency in complex environments, particularly in tasks where efficient exploration is a bottleneck.
no code implementations • 1 Jan 2021 • Nathan Grinsztajn, Philippe Preux, Edouard Oyallon
In this work, we study the behavior of standard GCNs under spectral manipulations.
1 code implementation • 9 Nov 2020 • Nathan Grinsztajn, Olivier Beaumont, Emmanuel Jeannot, Philippe Preux
In this paper, we propose a reinforcement learning approach to solve a realistic scheduling problem, and apply it to an algorithm commonly executed in the high performance computing community, the Cholesky factorization.
no code implementations • ICLR 2021 • Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux
We prove the theoretical consistency of the new gradient estimator and observe dramatic empirical improvement across a variety of continuous control tasks and algorithms.
no code implementations • 7 Aug 2020 • Mathieu Seurin, Florian Strub, Philippe Preux, Olivier Pietquin
To do so, we cast the speaker recognition task into a sequential decision-making problem that we solve with Reinforcement Learning.
no code implementations • 4 Oct 2019 • Mathieu Seurin, Philippe Preux, Olivier Pietquin
Violating constraints thus results in rejected actions or entering in a safe mode driven by an external controller, making RL agents incapable of learning from their mistakes.
no code implementations • 26 Sep 2019 • Yannis Flet-Berliac, Philippe Preux
In this paper: (a) We introduce and define MERL, the multi-head reinforcement learning framework we use throughout this work.
no code implementations • 25 Sep 2019 • Yannis Flet-Berliac, Philippe Preux
In this work, Vex is used to evaluate the impact each transition will have on learning: this criterion refines sampling and improves the policy gradient algorithm.
no code implementations • 8 Apr 2019 • Yannis Flet-Berliac, Philippe Preux
In this work, we use this metric to select samples that are useful to learn from, and we demonstrate that this selection can significantly improve the performance of policy gradient methods.
1 code implementation • ECCV 2018 • Florian Strub, Mathieu Seurin, Ethan Perez, Harm de Vries, Jérémie Mary, Philippe Preux, Aaron Courville, Olivier Pietquin
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue.
no code implementations • 23 Jul 2018 • Kiewan Villatel, Elena Smirnova, Jérémie Mary, Philippe Preux
Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon.
no code implementations • 28 Oct 2015 • Hachem Kadri, Emmanuel Duflos, Philippe Preux, Stéphane Canu, Alain Rakotomamonjy, Julien Audiffren
In this paper we consider the problems of supervised classification and regression in the case where attributes and labels are functions: a data is represented by a set of functions, and the label is also a function.
2 code implementations • 29 Oct 2014 • Vincenzo Musco, Martin Monperrus, Philippe Preux
Then, we propose a generative model of software dependency graphs which synthesizes graphs whose degree distribution is close to the empirical ones observed in real software systems.
Software Engineering
no code implementations • 14 May 2014 • Olivier Nicol, Jérémie Mary, Philippe Preux
In general the evaluation of a RS is a critical issue.
no code implementations • NeurIPS 2012 • Hachem Kadri, Alain Rakotomamonjy, Philippe Preux, Francis R. Bach
We study this problem in the case of kernel ridge regression for functional responses with an lr-norm constraint on the combination coefficients.
no code implementations • 10 May 2012 • Hachem Kadri, Mohammad Ghavamzadeh, Philippe Preux
Finally, we evaluate the performance of our KDE approach using both covariance and conditional covariance kernels on two structured output problems, and compare it to the state-of-the-art kernel-based structured output regression methods.