Search

Nathan Grinsztajn

Combinatorial Optimization with Policy Adaptation using Latent Space Search
Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
MetaREVEAL: RL-based Meta-learning from Learning Curves
There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning
READYS: A Reinforcement Learning Based Strategy for Heterogeneous Dynamic Scheduling
Interferometric Graph Transform for Community Labeling
Low-Rank Projections of GCNs Laplacian
Geometric Deep Reinforcement Learning for Dynamic DAG Scheduling