no code implementations • 14 Oct 2022 • Albert Wilcox, Ashwin Balakrishna, Jules Dedieu, Wyame Benslimane, Daniel S. Brown, Ken Goldberg
Providing densely shaped reward functions for RL algorithms is often exceedingly challenging, motivating the development of RL algorithms that can learn from easier-to-specify sparse reward functions.
no code implementations • 4 Sep 2021 • Gauthier Roy, Jules Dedieu, Capucine Bertrand, Alireza Moshayedi, Ali Mammadov, Stéphanie Petit, Saima Ben Hadj, Rutger H. J. Fick
Our main algorithmic choices are as follows: first, to enhance the generalizability of our detector and classification networks, we use a state-of-the-art residual Cycle-GAN to transform each scanner domain to every other scanner domain.