no code implementations • 2 Oct 2020 • Wolfgang Merkt, Vladimir Ivan, Traiko Dinev, Ioannis Havoutis, Sethu Vijayakumar
We demonstrate our method on a cart-pole toy problem and a quadrotor avoiding obstacles, and show that clustering samples based on inherent structure improves the warm-start quality.
no code implementations • 23 Oct 2018 • Traiko Dinev, Michael U. Gutmann
While several methods for choosing summary statistics have been proposed for ABC, the literature for synthetic likelihood and LFIRE is very thin to date.