Publications

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Applying reinforcement learning (RL) to combinatorial optimization problems is attractive as it removes the need for expert knowledge …

Nathan Grinsztajn, Daniel Furelos-Blanco, Shikha Surana, Clément Bonnet, Thomas D. Barrett

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Combinatorial Optimization with Policy Adaptation using Latent Space Search

Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, …

Felix Chalumeau, Shikha Surana, Clément Bonnet, Nathan Grinsztajn, Arnu Pretorius, Alexandre Laterre, Thomas D. Barrett

More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences

Incorporating prior knowledge in reinforcement learning algorithms is mainly an open question. Even when insights about the environment …

Nathan Grinsztajn, Toby Johnstone, Johan Ferret, Philippe Preux

MetaREVEAL: RL-based Meta-learning from Learning Curves

This paper addresses a cornerstone of Automated Machine Learning: the problem of rapidly uncovering which machine learning algorithm …

Manh Hung Nguyen, Nathan Grinsztajn, Lisheng Sun-Hosoya, Isabelle Guyon

MetaREVEAL: RL-based Meta-learning from Learning Curves

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

We propose to learn to distinguish reversible from irreversible actions for better informed decision-making in Reinforcement Learning …

Nathan Grinsztajn, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist

There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning

READYS: A Reinforcement Learning Based Strategy for Heterogeneous Dynamic Scheduling

In this paper, we propose READYS, a reinforcement learning algorithm for the dynamic scheduling of computations modeled as a Directed …

Nathan Grinsztajn, Olivier Beaumont, Emmanuel Jeannot, Philippe Preux

Interferometric Graph Transform for Community Labeling

We present a new approach for learning unsupervised node representations in community graphs. We significantly extend the …

Nathan Grinsztajn, Louis Leconte, Philippe Preux, Edouard Oyallon

Low-Rank Projections of GCNs Laplacian

In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation …

Nathan Grinsztajn, Philippe Preux, Edouard Oyallon

Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling

In practice, it is quite common to face combinatorial optimization problems which contain uncertainty along with non-determinism and …

Nathan Grinsztajn, Olivier Beaumont, Emmanuel Jeannot, Philippe Preux

Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling