1 code implementation • ICLR 2022 • Petra Poklukar, Vladislav Polianskii, Anastasia Varava, Florian Pokorny, Danica Kragic
Advanced representation learning techniques require reliable and general evaluation methods.
no code implementations • 8 Feb 2022 • Ciwan Ceylan, Petra Poklukar, Hanna Hultin, Alexander Kravchenko, Anastasia Varava, Danica Kragic
We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics which are often used in practice, especially to evaluate graph generative models.
no code implementations • 14 Sep 2021 • Constantinos Chamzas, Martina Lippi, Michael C. Welle, Anastasia Varava, Lydia E. Kavraki, Danica Kragic
Most methods learn state representations by utilizing losses based on the reconstruction of the raw observations from a lower-dimensional latent space.
1 code implementation • 26 May 2021 • Petra Poklukar, Anastasia Varava, Danica Kragic
Evaluating the quality of learned representations without relying on a downstream task remains one of the challenges in representation learning.
1 code implementation • 3 Mar 2021 • Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasia Varava, Hang Yin, Alessandro Marino, Danica Kragic
We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects.