no code implementations • 6 Dec 2021 • Julien Brosseit, Benedikt Hahner, Fabio Muratore, Michael Gienger, Jan Peters
However, these methods are notorious for the enormous amount of required training data which is prohibitively expensive to collect on real robots.
no code implementations • 1 Nov 2021 • Fabio Muratore, Fabio Ramos, Greg Turk, Wenhao Yu, Michael Gienger, Jan Peters
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.
1 code implementation • 20 Jul 2021 • João Carvalho, Davide Tateo, Fabio Muratore, Jan Peters
This estimator is unbiased, has low variance, and can be used with differentiable and non-differentiable function approximators.
no code implementations • 5 Mar 2020 • Fabio Muratore, Christian Eilers, Michael Gienger, Jan Peters
Domain randomization methods tackle this problem by randomizing the physics simulator (source domain) during training according to a distribution over domain parameters in order to obtain more robust policies that are able to overcome the reality gap.
no code implementations • 10 Jul 2019 • Fabio Muratore, Michael Gienger, Jan Peters
Optimizing a policy on a slightly faulty simulator can easily lead to the maximization of the `Simulation Optimization Bias` (SOB).