no code implementations • 12 Feb 2024 • Sahel Iqbal, Adrien Corenflos, Simo Särkkä, Hany Abdulsamad
In this paper, we propose a novel approach to Bayesian experimental design for non-exchangeable data that formulates it as risk-sensitive policy optimization.
1 code implementation • 21 Dec 2023 • Hany Abdulsamad, Sahel Iqbal, Adrien Corenflos, Simo Särkkä
Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making.
no code implementations • 15 Jun 2023 • Fatemeh Yaghoobi, Hany Abdulsamad, Simo Särkkä
In this paper, we use the optimization formulation of nonlinear Kalman filtering and smoothing problems to develop second-order variants of iterated Kalman smoother (IKS) methods.
1 code implementation • 11 Mar 2023 • Adrien Corenflos, Hany Abdulsamad
We present a novel approach to approximate Gaussian and mixture-of-Gaussians filtering.
no code implementations • 2 Nov 2022 • Hany Abdulsamad, Peter Nickl, Pascal Klink, Jan Peters
We derive two efficient variational inference techniques to learn these representations and highlight the advantages of hierarchical infinite local regression models, such as dealing with non-smooth functions, mitigating catastrophic forgetting, and enabling parameter sharing and fast predictions.
no code implementations • 1 Jun 2022 • Tim Schneider, Boris Belousov, Hany Abdulsamad, Jan Peters
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in the last decades.
no code implementations • 11 Nov 2021 • Hany Abdulsamad, Jan Peters
Optimal control of general nonlinear systems is a central challenge in automation.
1 code implementation • 17 May 2021 • Joe Watson, Hany Abdulsamad, Rolf Findeisen, Jan Peters
Optimal control under uncertainty is a prevailing challenge for many reasons.
no code implementations • 29 Mar 2021 • Hany Abdulsamad, Tim Dorau, Boris Belousov, Jia-Jie Zhu, Jan Peters
Trajectory optimization and model predictive control are essential techniques underpinning advanced robotic applications, ranging from autonomous driving to full-body humanoid control.
1 code implementation • 25 Feb 2021 • Pascal Klink, Hany Abdulsamad, Boris Belousov, Carlo D'Eramo, Jan Peters, Joni Pajarinen
Across machine learning, the use of curricula has shown strong empirical potential to improve learning from data by avoiding local optima of training objectives.
1 code implementation • 10 Nov 2020 • Hany Abdulsamad, Peter Nickl, Pascal Klink, Jan Peters
Probabilistic regression techniques in control and robotics applications have to fulfill different criteria of data-driven adaptability, computational efficiency, scalability to high dimensions, and the capacity to deal with different modalities in the data.
no code implementations • L4DC 2020 • Hany Abdulsamad, Jan Peters
The control of nonlinear dynamical systems remains a major challenge for autonomous agents.
1 code implementation • 8 Jan 2020 • Samuele Tosatto, Joao Carvalho, Hany Abdulsamad, Jan Peters
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes.
1 code implementation • 8 Oct 2019 • Matthias Schultheis, Boris Belousov, Hany Abdulsamad, Jan Peters
Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion.
1 code implementation • Conference on Robot Learning (CoRL) 2019 2019 • Joe Watson, Hany Abdulsamad, Jan Peters
Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning.
1 code implementation • 7 Oct 2019 • Pascal Klink, Hany Abdulsamad, Boris Belousov, Jan Peters
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots.
no code implementations • 29 Jun 2016 • Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad, Jan Peters, Gerhard Neumann
In order to show the monotonic improvement of our algorithm, we additionally conduct a theoretical analysis of our policy update scheme to derive a lower bound of the change in policy return between successive iterations.