no code implementations • 2 Aug 2023 • Michel Aractingi, Pierre-Alexandre Léziart, Thomas Flayols, Julien Perez, Tomi Silander, Philippe Souères
We detail the learning procedure and method for transfer on the real robot.
no code implementations • ICLR 2020 • Michel Aractingi, Christopher Dance, Julien Perez, Tomi Silander
The results of this method, called invariance regularization, show an improvement in the generalization of policies to environments not seen during training.