2 papers
cs.LG2026
Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching
Andrea Fraschini, Davide Tenedini, Riccardo Zamboni +2
Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inh…
math.NA2025
MAGNET: an open-source library for mesh agglomeration by Graph Neural Networks
Paola F. Antonietti, Matteo Caldana, Ilario Mazzieri +1
We introduce MAGNET, an open-source Python library designed for mesh agglomeration in both two- and three-dimensions, based on employing Graph Neural Networks (GNN). MAGNET serves…