Articles with public access mandates - Hany AbdulsamadLearn more
Available somewhere: 18
Robust reinforcement learning: A review of foundations and recent advances
J Moos, K Hansel, H Abdulsamad, S Stark, D Clever, J Peters
Machine Learning and Knowledge Extraction 4 (1), 276-315, 2022
Mandates: German Research Foundation
Self-paced contextual reinforcement learning
P Klink, H Abdulsamad, B Belousov, J Peters
Conference on Robot Learning, 513-529, 2020
Mandates: German Research Foundation, European Commission
Model-free trajectory optimization for reinforcement learning
R Akrour, G Neumann, H Abdulsamad, A Abdolmaleki
International Conference on Machine Learning, 2961-2970, 2016
Mandates: German Research Foundation
Stochastic optimal control as approximate input inference
J Watson, H Abdulsamad, J Peters
Conference on Robot Learning, 697-716, 2020
Mandates: European Commission
Model-free trajectory-based policy optimization with monotonic improvement
R Akrour, A Abdolmaleki, H Abdulsamad, J Peters, G Neumann
Journal of machine learning research 19 (14), 1-25, 2018
Mandates: German Research Foundation, European Commission
A probabilistic interpretation of self-paced learning with applications to reinforcement learning
P Klink, H Abdulsamad, B Belousov, C D'Eramo, J Peters, J Pajarinen
Journal of Machine Learning Research 22 (182), 1-52, 2021
Mandates: German Research Foundation, European Commission
Receding horizon curiosity
M Schultheis, B Belousov, H Abdulsamad, J Peters
Conference on robot learning, 1278-1288, 2020
Mandates: European Commission
Reinforcement learning vs human programming in tetherball robot games
S Parisi, H Abdulsamad, A Paraschos, C Daniel, J Peters
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2015
Mandates: German Research Foundation
A nonparametric off-policy policy gradient
S Tosatto, J Carvalho, H Abdulsamad, J Peters
International Conference on Artificial Intelligence and Statistics, 167-177, 2020
Mandates: European Commission
Hierarchical decomposition of nonlinear dynamics and control for system identification and policy distillation
H Abdulsamad, J Peters
Learning for Dynamics and Control, 904-914, 2020
Mandates: European Commission
Chance-constrained trajectory optimization for non-linear systems with unknown stochastic dynamics
O Celik, H Abdulsamad, J Peters
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2019
Mandates: European Commission
Optimal control and inverse optimal control by distribution matching
O Arenz, H Abdulsamad, G Neumann
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2016
Mandates: European Commission
A variational infinite mixture for probabilistic inverse dynamics learning
H Abdulsamad, P Nickl, P Klink, J Peters
2021 IEEE International Conference on Robotics and Automation (ICRA), 4216-4222, 2021
Mandates: German Research Foundation, European Commission
State-regularized policy search for linearized dynamical systems
H Abdulsamad, O Arenz, J Peters, G Neumann
Proceedings of the International Conference on Automated Planning and …, 2017
Mandates: European Commission
Belief space model predictive control for approximately optimal system identification
B Belousov, H Abdulsamad, M Schultheis, J Peters
Multidisciplinary Conference on Reinforcement Learning and Decision Making, 2019
Mandates: European Commission
Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics
H Abdulsamad, P Nickl, P Klink, J Peters
IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (4), 1950-1963, 2023
Mandates: European Commission
A recursive newton method for smoothing in nonlinear state space models
F Yaghoobi, H Abdulsamad, S Särkkä
2023 31st European Signal Processing Conference (EUSIPCO), 1758-1762, 2023
Mandates: Academy of Finland
Variational Gaussian filtering via Wasserstein gradient flows
A Corenflos, H Abdulsamad
2023 31st European Signal Processing Conference (EUSIPCO), 1838-1842, 2023
Mandates: Academy of Finland
Publication and funding information is determined automatically by a computer program