no code implementations • 17 Feb 2023 • Ruohan Wang, Zhiyong Sun
Electrical grids are large-sized complex systems that require strong computing power for monitoring and analysis.
1 code implementation • 22 Dec 2022 • Ruohan Wang, Isak Falk, Massimiliano Pontil, Carlo Ciliberto
Empirically, MeLa outperforms existing methods across a diverse range of benchmarks, in particular under a more challenging setting where the number of training tasks is limited and labels are task-specific.
no code implementations • 11 Oct 2022 • Ruohan Wang, Marco Ciccone, Giulia Luise, Andrew Yapp, Massimiliano Pontil, Carlo Ciliberto
A continual learning (CL) algorithm learns from a non-stationary data stream.
no code implementations • NeurIPS 2021 • Ruohan Wang, Massimiliano Pontil, Carlo Ciliberto
Few-shot learning is a central problem in meta-learning, where learners must quickly adapt to new tasks given limited training data.
1 code implementation • NeurIPS 2020 • Ruohan Wang, Yiannis Demiris, Carlo Ciliberto
We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-specific objective functions by weighing meta-training data on target tasks.
no code implementations • 20 Feb 2020 • Ruohan Wang, Carlo Ciliberto, Pierluigi Amadori, Yiannis Demiris
To address the challenges, we propose Support-weighted Adversarial Imitation Learning (SAIL), a general framework that extends a given AIL algorithm with information derived from support estimation of the expert policies.
no code implementations • 25 Sep 2019 • Ruohan Wang, Carlo Ciliberto, Pierluigi Amadori, Yiannis Demiris
We propose Support-guided Adversarial Imitation Learning (SAIL), a generic imitation learning framework that unifies support estimation of the expert policy with the family of Adversarial Imitation Learning (AIL) algorithms.
2 code implementations • 16 May 2019 • Ruohan Wang, Carlo Ciliberto, Pierluigi Amadori, Yiannis Demiris
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals.
no code implementations • 7 Oct 2018 • Ruohan Wang, Pierluigi V. Amadori, Yiannis Demiris
Classifying human cognitive states from behavioral and physiological signals is a challenging problem with important applications in robotics.
1 code implementation • 12 Apr 2017 • Ruohan Wang, Antoine Cully, Hyung Jin Chang, Yiannis Demiris
We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function.