3 papers
cs.RO2023★ 1 cited
Graph learning in robotics: a survey
Francesca Pistilli, Giuseppe Averta
Deep neural networks for graphs have emerged as a powerful tool for learning on complex non-euclidean data, which is becoming increasingly common for a variety of different applica…
cs.CV2023
Entropic Score metric: Decoupling Topology and Size in Training-free NAS
Niccolò Cavagnero, Luca Robbiano, Francesca Pistilli +2
Neural Networks design is a complex and often daunting task, particularly for resource-constrained scenarios typical of mobile-sized models. Neural Architecture Search is a promisi…
cs.RO2022
Online vs. Offline Adaptive Domain Randomization Benchmark
Gabriele Tiboni, Karol Arndt, Giuseppe Averta +2
Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowle…