1 code implementation • NeurIPS 2023 • Dominik Straub, Matthias Schultheis, Heinz Koeppl, Constantin A. Rothkopf
Inverse optimal control can be used to characterize behavior in sequential decision-making tasks.
no code implementations • 27 Sep 2022 • Matthias Schultheis, Constantin A. Rothkopf, Heinz Koeppl
In contrast, in economics and psychology, it has been shown that humans often adopt a hyperbolic discounting scheme, which is optimal when a specific task termination time distribution is assumed.
1 code implementation • NeurIPS 2021 • Matthias Schultheis, Dominik Straub, Constantin A. Rothkopf
Computational level explanations based on optimal feedback control with signal-dependent noise have been able to account for a vast array of phenomena in human sensorimotor behavior.
no code implementations • NeurIPS 2020 • Bastian Alt, Matthias Schultheis, Heinz Koeppl
We consider the problem of optimal decision making in such discrete state and action space systems under partial observability.
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 • 29 May 2018 • Maximilian Sieb, Matthias Schultheis, Sebastian Szelag, Rudolf Lioutikov, Jan Peters
Using movement primitive libraries is an effective means to enable robots to solve more complex tasks.