no code implementations • 21 Dec 2023 • Cristian Axenie, Oliver López-Corona, Michail A. Makridis, Meisam Akbarzadeh, Matteo Saveriano, Alexandru Stancu, Jeffrey West
Antifragility characterizes the benefit of a dynamical system derived from the variability in environmental perturbations.
no code implementations • 4 Nov 2023 • Hector Perez-Villeda, Justus Piater, Matteo Saveriano
While conventional approaches for constrained regression use one kind of basis function, e. g., Gaussian, we exploit Equation Learner Networks to learn a set of analytical expressions and use them as basis functions.
1 code implementation • 9 Nov 2022 • Antonio Rodríguez-Sánchez, Simon Haller-Seeber, David Peer, Chris Engelhardt, Jakob Mittelberger, Matteo Saveriano
In the experimental evaluation we will show that our algorithm is superior to current affordance detection methods when faced with grasping previously unseen objects thanks to our Capsule Network enforcing a parts-to-whole representation.
no code implementations • 8 Jun 2022 • Jakob Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater
Many Deep Reinforcement Learning (D-RL) algorithms rely on simple forms of exploration such as the additive action noise often used in continuous control domains.
1 code implementation • 14 Feb 2022 • Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano, Antonio Rodríguez-Sánchez, Justus Piater
We empirically demonstrate the effectiveness of this approach in remembering long sequences of trajectory learning tasks without the need to store any data from past demonstrations.
no code implementations • 20 Oct 2021 • Fares J. Abu-Dakka, Matteo Saveriano, Luka Peternel
While DMPs have been properly formulated for learning point-to-point movements for both translation and orientation, periodic ones are missing a formulation to learn the orientation.
no code implementations • 11 Jun 2021 • Gennaro Notomista, Matteo Saveriano
This paper presents an approach to deal with safety of dynamical systems in presence of multiple non-convex unsafe sets.
no code implementations • 29 Oct 2020 • Jakob J. Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater
Sufficient exploration is paramount for the success of a reinforcement learning agent.
no code implementations • 24 Oct 2020 • Jakob J. Hollenstein, Erwan Renaudo, Matteo Saveriano, Justus Piater
Local policy search is performed by most Deep Reinforcement Learning (D-RL) methods, which increases the risk of getting trapped in a local minimum.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 20 Nov 2019 • Pietro Falco, Matteo Saveriano, Eka Gibran Hasany, Nicholas H. Kirk, Dongheui Lee
The second step enriches the descriptor considering minimum and maximum joint velocities and the correlations between the most informative joints.
no code implementations • 20 Nov 2019 • Pietro Falco, Abdallah Attawia, Matteo Saveriano, Dongheui Lee
This way, the occurrence of object slipping during the learning procedure, which we consider an irreversible event, is significantly reduced.