Подписаться
Jan Robine
Jan Robine
Technical University of Dortmund
Подтвержден адрес электронной почты в домене tu-dortmund.de
Название
Процитировано
Процитировано
Год
Transformer-based world models are happy with 100k interactions
J Robine, M Höftmann, T Uelwer, S Harmeling
arXiv preprint arXiv:2303.07109, 2023
272023
Smaller world models for reinforcement learning
J Robine, T Uelwer, S Harmeling
Neural Processing Letters 55 (8), 11397-11427, 2023
8*2023
Time-myopic go-explore: Learning a state representation for the go-explore paradigm
M Höftmann, J Robine, S Harmeling
arXiv preprint arXiv:2301.05635, 2023
32023
A survey on self-supervised representation learning
T Uelwer, J Robine, SS Wagner, M Höftmann, E Upschulte, S Konietzny, ...
arXiv preprint arXiv:2308.11455, 2023
22023
Limited-angle tomography reconstruction via deep end-to-end learning on synthetic data
T Germer, J Robine, S Konietzny, S Harmeling, T Uelwer
arXiv preprint arXiv:2309.06948, 2023
12023
Backward Learning for Goal-Conditioned Policies
M Höftmann, J Robine, S Harmeling
arXiv preprint arXiv:2312.05044, 2023
2023
Cyclophobic Reinforcement Learning
SS Wagner, P Arndt, J Robine, S Harmeling
arXiv preprint arXiv:2308.15911, 2023
2023
Cyclophobic Reinforcement Learning
S Sylvius Wagner, P Arndt, J Robine, S Harmeling
arXiv e-prints, arXiv: 2308.15911, 2023
2023
A Simple Framework for Self-Supervised Learning of Sample-Efficient World Models
J Robine, M Höftmann, S Harmeling
Dyna 31 (16), 17-18, 0
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–9