no code implementations • 3 Oct 2023 • Jin Cheng, Marin Vlastelica, Pavel Kolev, Chenhao Li, Georg Martius
We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon.
no code implementations • 11 Sep 2023 • Marin Vlastelica, Sebastian Blaes, Cristina Pineri, Georg Martius
We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.
no code implementations • 5 Sep 2023 • Marin Vlastelica, Tatiana López-Guevara, Kelsey Allen, Peter Battaglia, Arnaud Doucet, Kimberley Stachenfeld
Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome.
no code implementations • 21 Jul 2023 • Marin Vlastelica, Jin Cheng, Georg Martius, Pavel Kolev
There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity.
no code implementations • 19 Jul 2023 • Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu, Marin Vlastelica, Julius von Kügelgen, Bernhard Schölkopf
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose relationship with the label changes across domains.
no code implementations • 16 Sep 2022 • Chenhao Li, Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey, Georg Martius
Learning diverse skills is one of the main challenges in robotics.
no code implementations • 23 Jun 2022 • Chenhao Li, Marin Vlastelica, Sebastian Blaes, Jonas Frey, Felix Grimminger, Georg Martius
Learning agile skills is one of the main challenges in robotics.
2 code implementations • 30 May 2022 • Subham Sekhar Sahoo, Anselm Paulus, Marin Vlastelica, Vít Musil, Volodymyr Kuleshov, Georg Martius
Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities.
Ranked #1 on Density Estimation on MNIST
no code implementations • 16 May 2022 • Marin Vlastelica, Patrick Ernst, György Szarvas
Utilizing amortized variational inference for latent-action reinforcement learning (RL) has been shown to be an effective approach in Task-oriented Dialogue (ToD) systems for optimizing dialogue success.
no code implementations • 15 Feb 2021 • Marin Vlastelica, Michal Rolínek, Georg Martius
Furthermore, we show that for a certain subclass of the MDP framework, this can be alleviated by neuro-algorithmic architectures.
1 code implementation • 7 Dec 2019 • Michal Rolínek, Vít Musil, Anselm Paulus, Marin Vlastelica, Claudio Michaelis, Georg Martius
Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models.
7 code implementations • ICLR 2020 • Marin Vlastelica, Anselm Paulus, Vít Musil, Georg Martius, Michal Rolínek
Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence.