no code implementations • 4 Mar 2024 • Gianluca Baldassarre, Richard J. Duro, Emilio Cartoni, Mehdi Khamassi, Alejandro Romero, Vieri Giuliano Santucci
Overall, the approach enables OEL robots to learn in an autonomous way but also to focus on acquiring goals and skills that meet the purposes of the designers and users.
no code implementations • 13 May 2020 • Stephane Doncieux, Nicolas Bredeche, Léni Le Goff, Benoît Girard, Alexandre Coninx, Olivier Sigaud, Mehdi Khamassi, Natalia Díaz-Rodríguez, David Filliat, Timothy Hospedales, A. Eiben, Richard Duro
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors.
no code implementations • 30 Apr 2020 • Rémi Dromnelle, Erwan Renaudo, Guillaume Pourcel, Raja Chatila, Benoît Girard, Mehdi Khamassi
We present a novel arbitration mechanism between learning systems that explicitly measures performance and cost.
no code implementations • 1 Dec 2018 • Jack Hadfield, Georgia Chalvatzaki, Petros Koutras, Mehdi Khamassi, Costas S. Tzafestas, Petros Maragos
In this work we tackle the problem of child engagement estimation while children freely interact with a robot in their room.
no code implementations • 15 Feb 2018 • Lise Aubin, Mehdi Khamassi, Benoît Girard
The Dyna reinforcement learning algorithms use off-line replays to improve learning.
1 code implementation • 2 Nov 2017 • Guillaume Viejo, Benoît Girard, Emmanuel Procyk, Mehdi Khamassi
We found that the behavior of the five monkeys was better explained in terms of a combination of RL and WM despite inter-individual differences.
1 code implementation • 6 Oct 2016 • Mehdi Khamassi, Costas Tzafestas
We apply a meta-learning algorithm based on the comparison between variations of short-term and long-term reward running averages to simultaneously tune $\beta$ and the width of the Gaussian distribution from which continuous action parameters are drawn.