no code implementations • 29 Sep 2021 • Michal Piovarci, Michael Foshey, Timothy Erps, Jie Xu, Vahid Babaei, Piotr Didyk, Wojciech Matusik, Szymon Rusinkiewicz, Bernd Bickel
We further show that in combination with reinforcement learning, our model can be used to discover control policies that outperform state-of-the-art controllers.