Follow
Nathan Grinsztajn
Title
Cited by
Cited by
Year
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
N Grinsztajn, J Ferret, O Pietquin, P Preux, M Geist
Neurips 2021, 2021
222021
Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
N Grinsztajn, D Furelos-Blanco, S Surana, C Bonnet, T Barrett
Advances in Neural Information Processing Systems 36, 2023
19*2023
Readys: A reinforcement learning based strategy for heterogeneous dynamic scheduling
N Grinsztajn, O Beaumont, E Jeannot, P Preux
2021 IEEE International Conference on Cluster Computing (CLUSTER), 70-81, 2021
192021
Jumanji: Industry-Driven Hardware-Accelerated RL Environments.(2022)
C Bonnet, D Byrne, V Le, L Midgley, D Luo, C Waters, S Abramowitz, ...
URL https://github. com/instadeepai/jumanji, 2022
16*2022
Combinatorial Optimization with Policy Adaptation using Latent Space Search
F Chalumeau, S Surana, C Bonnet, N Grinsztajn, A Pretorius, A Laterre, ...
Thirty-seventh Conference on Neural Information Processing Systems, 2023
112023
Geometric deep reinforcement learning for dynamic DAG scheduling
N Grinsztajn, O Beaumont, E Jeannot, P Preux
2020 IEEE Symposium Series on Computational Intelligence (SSCI), 258-265, 2020
82020
MetaREVEAL: RL-based meta-learning from learning curves
MH Nguyen, N Grinsztajn, I Guyon, L Sun-Hosoya
Workshop on Interactive Adaptive Learning co-located with European …, 2021
52021
Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round
MH Nguyen, L Sun, N Grinsztajn, I Guyon
arXiv preprint arXiv:2208.02821, 2022
32022
Low-rank projections of GCNs laplacian
N Grinsztajn, P Preux, E Oyallon
ICLR 2021 Workshop on Geometrical and Topological Representation Learning, 2021
32021
Interferometric graph transform for community labeling
N Grinsztajn, L Leconte, P Preux, E Oyallon
arXiv preprint arXiv:2106.05875, 2021
32021
Are we going MAD? Benchmarking Multi-Agent Debate between Language Models for Medical Q&A
A Smit, P Duckworth, N Grinsztajn, K Tessera, TD Barrett, A Pretorius
arXiv preprint arXiv:2311.17371, 2023
22023
Better state exploration using action sequence equivalence
N Grinsztajn, T Johnstone, J Ferret, P Preux
NeurIPS 2022-Deep Reinforcement Learning Workshop, 2022
2*2022
Meta-learning from Learning Curves: Challenge Design and Baseline Results
MH Nguyen, L Sun-Hosoya, N Grinsztajn, I Guyon
2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022
12022
Averaging log-likelihoods in direct alignment
N Grinsztajn, Y Flet-Berliac, MG Azar, F Strub, B Wu, E Choi, C Cremer, ...
arXiv preprint arXiv:2406.19188, 2024
2024
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
Y Flet-Berliac, N Grinsztajn, F Strub, E Choi, C Cremer, A Ahmadian, ...
arXiv preprint arXiv:2406.19185, 2024
2024
Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optimization
F Chalumeau, R Shabe, N de Nicola, A Pretorius, TD Barrett, N Grinsztajn
arXiv preprint arXiv:2406.16424, 2024
2024
Apprentissage par renforcement pour l'optimisation combinatoire: exploiter l'incertitude, les structures et les connaissances a priori
N Grinsztajn
2023
Reinforcement learning for combinatorial optimization: leveraging uncertainty, structure and priors
N Grinsztajn
Université de Lille, 2023
2023
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
AP Smit, N Grinsztajn, P Duckworth, TD Barrett, A Pretorius
Forty-first International Conference on Machine Learning, 0
The system can't perform the operation now. Try again later.
Articles 1–19