5 papers
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
John Myron Uy
Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether unc…
Learning and Transferring Physical Models through Derivatives
Alessandro Trenta, Andrea Cossu, Davide Bacciu
We propose Derivative Learning (DERL), a supervised approach that models physical systems by learning their partial derivatives. We also leverage DERL to build physical models incr…
FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning
Alessandro Capurso, Elia Piccoli, Davide Bacciu
Transfer Learning (TL) offers the potential to accelerate learning by transferring knowledge across tasks. However, it faces critical challenges such as negative transfer, domain a…
Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning
Elia Piccoli, Malio Li, Giacomo Carfì +2
The recent focus and release of pre-trained models have been a key components to several advancements in many fields (e.g. Natural Language Processing and Computer Vision), as a ma…
Lifelong Evolution of Swarms
Lorenzo Leuzzi, Simon Jones, Sabine Hauert +2
Adapting to task changes without forgetting previous knowledge is a key skill for intelligent systems, and a crucial aspect of lifelong learning. Swarm controllers, however, are ty…